Stochastic Gradient Descent

Decentralized SGD is a fundamental algorithm in decentralized learning, although the influence of an underlying network topology on its convergence behavior is not yet fully understood. Existing convergence analyses have shown that topologies with a small spectral gap significantly deteriorate the convergence rate of Decentralized SGD in both homogeneous and heterogeneous cases. However, many prior papers have reported that indeed the choice of the topology has a significant experimental impact in the heterogeneous case, but has little experimental impact on training behavior in the homogeneous case. In this paper, we present a tighter convergence analysis of Decentralized SGD, offering a more precise understanding of how topologies affect the convergence rate than the prior analysis. Specifically, unlike existing convergence analyses that used only the spectral gap as a property of the topology, our novel analysis shows that all eigenvalues of the mixing matrix affect the convergence rate. Throughout the experiments, we carefully evaluated the convergence behavior of Decentralized SGD and demonstrated that our novel convergence analysis can more accurately describe the effect of topology on the convergence rate.

Predicting the generalization performance of deep neural networks without relying on hold-out validation data is a fundamental challenge in machine learning. While Stochastic Gradient Descent (SGD) drives the optimization of these highly parameterized models, its heavy-tailed, non-Gaussian dynamics induce complex, scale-invariant trajectories in the parameter space. In this paper, we propose a novel generalization measure based on the Fourier fractal dimension of the network's weight variations. By analyzing the characteristic function of the Lévy-driven stochastic differential equations in the frequency domain, we extract a metric that robustly captures the geometric complexity of the learning process. Furthermore, we introduce a customized Fourier-based optimizer designed to actively regularize this fractal dimension during training. Extensive empirical evaluations on the CIFAR-10, SVHN, and MNIST datasets demonstrate that our proposed Fourier generalization measure exhibits a strong correlation with the actual generalization gap. Our method achieves state-of-the-art Kendall rank correlation coefficients, outperforming a wide array of existing norm-based, margin-based, and PAC-Bayesian measures. Ultimately, this work highlights the potential of frequency-domain fractal analysis as both a powerful predictor for model generalizability and a principled foundation for developing more stable optimization algorithms.

Decentralized stochastic optimization is a fundamental paradigm for large-scale learning over networks, where agents communicate only with their neighbors and no central coordinator is required. For strongly convex problems, communication efficiency is mainly determined by the condition number $κ=L/μ$ and the network spectral gap $1-β$. Although deterministic decentralized methods can simultaneously achieve accelerated $\sqrtκ$ and $1/\sqrt{1-β}$ dependences, no existing stochastic method attains both improvements at once. In this paper, we propose \emph{Multi-Gossip Accelerated DSGD} (MG-ADSGD), a decentralized stochastic algorithm that combines Nesterov-type primal--dual extrapolation with multi-round fast gossip averaging. The key idea is to couple the gossip depth with the mini-batch size so that additional communication rounds simultaneously improve consensus accuracy and reduce gradient variance. We show that MG-ADSGD achieves the communication complexity $$\widetilde{\mathcal O}\!\left( \frac{σ^2}{μnε}\log\frac{1}ε + \sqrt{\fracκ{1-β}}\log\frac{1}ε \right),$$ where $ε$ denotes the target accuracy, $n$ is the number of nodes, and $σ^2$ is the gradient variance. To the best of our knowledge, this bound yields the best currently available communication complexity for decentralized stochastic strongly convex optimization, up to logarithmic factors that are independent of $ε$.

Understanding how training data shape neural network predictions is a central problem in modern learning theory. In 2020, Pedro Domingos proposed an interpolation formula valid for every model learned by deterministic gradient descent. It expresses the model's prediction as an integral, along the optimization path, of a data-dependent kernel that aligns the model's gradients at the test and training data. Such a first-order characterization remains valid for models trained with batch-based stochastic optimization. In this paper, we develop second-order forms of these interpolation formulas. We show that the leading path-kernel interpolation is supplemented by a curvature-weighted interpolation term. For stochastic gradient descent, an additional sampling-induced component appears, coupling the curvature of the prediction with the covariance of mini-batch gradient noise. We also extend the representation to stochastic gradient descent with momentum, where the interpolation structure is preserved but with the weights modified by a memory-related factor. Moreover, we establish a concentration estimate for the terminal prediction, identifying the fluctuation scale around the expected second-order representation. Together, these results provide a refinement of the path-kernel interpretation of neural network prediction.

Autoencoders (AEs) learn low-dimensional representations by mapping data into a latent space while minimizing reconstruction error. Despite their empirical success, theoretical understanding remains limited and largely restricted to linear models or settings without a bottleneck. In this work, we study nonlinear AEs with a fixed finite-dimensional bottleneck in the mean-field (MF) regime. We derive explicit MF learning dynamics for both encoder and decoder, providing a tractable characterization of training in the nonlinear setting. We show that, over finite time horizons, the empirical risk of finite-width networks trained with stochastic gradient descent closely tracks the MF risk trajectory with high probability. At optimality, we further establish that the finite-width risk converges to the MF optimum, demonstrating that finite networks are sufficiently expressive to approximate the infinite-width solution.

We analyze generalization error, uniform stability, and uniform argument stability of gradient descent (GD) and stochastic gradient descent (SGD) over discrete parameter spaces, where each update involves deterministic or stochastic rounding. We show that deterministic rounding degrades the generalization error of GD on convex, Lipschitz, and smooth loss functions, increasing the rate from $O(T/n)$ to $O(T/\sqrt{n})$, and establish matching lower bounds. We further prove that uniform stability of GD becomes $Ω(T)$, showing that stability-based generalization bounds are vacuous in this setting. In contrast, for the same losses, stochastic gradient descent with deterministic rounding admits nontrivial uniform stability guarantees, which differ qualitatively from the real-valued case and exhibit distinct dependencies on the number of iterations and the dimension: we prove tight bounds $O(T/n)$ for one dimension and $O(T^2/n)$ for higher dimensions. We also show that stochastic rounding can introduce generalization error that increases with the dimension; such a phenomenon is absent in standard real-valued optimization and in the deterministic rounding case. Finally, we provide upper bounds on uniform argument stability for stochastic rounding schemes and show that these bounds are tight when the loss can be represented as a sum of coordinate-wise functions.

Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory. While recent advances, particularly works under the Neural Tangent Kernel (NTK) regime, have shed light on the behavior of shallow architectures, the statistical generalization properties of deep neural networks (DNNs), especially in regression tasks, remain far less understood. In this paper, we make significant progress toward closing this gap by providing a comprehensive generalization analysis of DNNs trained using gradient-based methods. First, we establish, for the first time, a crucial connection between the learning dynamics of a DNN with smooth activation functions trained via gradient-based methods and those of kernel methods, showing that gradient-based methods on over-parameterized DNNs can fully inherit the favorable learning dynamics of their kernel counterparts. Building on this connection and the well-established optimality of kernel methods, we derive the first known minimax-optimal rates for the excess population risk of both gradient descent (GD) and stochastic gradient descent (SGD), under the assumption that network width scales polynomially with the sample size. Our results demonstrate that, with sufficient width, DNNs trained by GD or SGD can achieve generalization performance comparable to kernel-based methods.

Recent progress has been made in understanding the statistical generalization performance of gradient descent methods for overparameterized neural networks within the neural tangent kernel (NTK) regime. However, most of the existing work on regression problems is limited to shallow network architectures, leaving a notable gap in the theory of deep neural networks. This paper addresses this gap by presenting a comprehensive generalization analysis for deep ReLU networks trained using gradient descent (GD) and stochastic gradient descent (SGD). Specifically, we establish the first known minimax-optimal rates of excess population risk for both GD and SGD with deep ReLU networks, under the assumption that the network width scales polynomially with respect to the network depth and training sample size. Our results demonstrate that with sufficient width, gradient descent methods for deep ReLU networks can achieve optimal generalization rates on par with kernel methods.

Uncertainty quantification in neural networks prediction is a main issue for usual applications. Our approach seeks at reducing computation costs by directly evaluating uncertainty using PDE's information on the asymptotic variance, rather than the deep ensemble method which may be seen as a Monte Carlo estimation of the prediction, requiring the training of multiple networks. We thus study the law of the limiting process describing the random fluctuations around the mean-field limit of wide two-layer neural networks trained by stochastic gradient descent in a weak-noise regime. Building on a recent trajectorial central limit theorem, in which this limit is characterized as the weak solution of a linear stochastic evolution equation, we identify its law explicitly. More precisely, we show that it is a centered Gaussian process in the dual of a weighted Sobolev space, and we derive a closed covariance representation for the finite-dimensional distributions obtained by testing it against smooth functions. This covariance is expressed through the solution of a backward transport equation with a nonlocal source term, whose coefficients are driven by the mean-field trajectory. As a consequence, by testing against the activation function at a fixed input, we obtain an expression for the limiting variance of the corresponding network-output fluctuations. We illustrate this result numerically on a one-dimensional regression example.

Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping threshold to limit sensitivity remains a significant practical limitation. Adaptive clipping algorithms such as AdaClip shift and scale the gradient prior to clipping and adding noise so that the clipped gradient yields a more informative descent direction. The shift and scaling parameters are selected adaptively based on the empirical mean and variance. However, in existing adaptive clipping algorithms, these empirical estimates have not been also used for momentum to accelerate training itself. On the other hand, DP-Adam is an algorithm that exploits Adam-like momentum updates based on the gradient mean and variance to accelerate training, but does not exploit these estimates for adaptive clipping. In this work, we propose Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum (DP-MacAdam), a novel algorithm that combines these two approaches so as to use the same mean and variance estimates for both clipping and momentum. We perform an analysis showing that DP-MacAdam estimates the gradient variances in a bias-free manner. In addition, we empirically evaluate the privacy and accuracy of DP-MacAdam, demonstrating that it achieves improved model utility compared to DP-SGD, AdaClip, and DP-Adam baselines, without requiring manual tuning of the clipping threshold.

Stochastic gradient Langevin algorithms often use tamed denominators to stabilize superlinear drifts. This paper shows that when the denominator depends on the current stochastic gradient, the transformed update can have a biased conditional mean even if the original stochastic gradient is unbiased. This creates a stationary mean-shift channel that is absent for deterministic denominators.We propose a structure-preserving framework for designing tamed denominators. The construction keeps the denominator deterministic given the current state, and uses localized deterministic envelopes to avoid unnecessary taming in typical regions. These kernels retain the stabilizing effect of taming while avoiding the bias introduced by a gradient-dependent denominator. Our theory bounds the stationary bias through Euler, envelope, and stochastic-gradient residuals. The analysis also shows why purely local taming rules can lose control in the far tail and motivates a hybrid construction with additional tail protection. Experiments confirm the stationary distortions of random denominators, the bias reduction of deterministic-envelope designs, and the stabilizing effect of the hybrid construction.

In the paradigm of decentralized learning, a group of agents collaborate to train a global model using distributed datasets without a central server. Although the power of collaboration has been verified by many state-of-the-art studies, it entails extensive gradient information exchanging among the agents and thus induces high risk of privacy leakage for the individual agents. Moreover, in real-world applications, the training data are usually non-identically and independently distributed across the agents, inducing more challenges to enable privacy-preserved decentralized learning. To address these issues, we propose a privacy-preserved decentralized learning algorithm with non-IID data, DPDL, which leverages the notion of Differential Privacy (DP) in cross-gradient aggregation through a similarity-based calibration technique. Specifically, in each round, each agent perturbs the cross-gradients (i.e., the derivatives of its neighbors' local model in its private local data) by Gaussian noise mechanism before sharing them with its neighbors; it then adopt cosine similarity to calibrate the received perturbed cross-gradients such that the aggregation of the calibrated cross-gradients can be utilized to effectively update local model in a momentum-like manner. Our rigorous theoretical analysis not only reveals the minimum noise level required to achieve a specific level of privacy preservation, but also illustrates that our algorithm still achieves a linear speedup in training with non-IID data. We finally conduct extensive experiments on real-world dataset to validate the effectiveness of our algorithm in defending privacy attacks and in training accurate models.

Machine learning's reliance on sensitive data necessitates privacy-preserving techniques like Differentially Private Stochastic Gradient Descent (DPSGD). However, DPSGD suffers from substantial utility degradation and slow convergence due to gradient clipping and noise injection. Prior works have attempted to improve DPSGD from various perspectives; notably, the Differentially Private Selective Update and Release (DPSUR) algorithm has achieved remarkable model utility. However, the privacy accounting in DPSUR overlooks the variation in sampling probability introduced by the selective release mechanism, which compromises the rigor of its privacy guarantees. To address these limitations, we re-evaluate the privacy analysis of the selective release mechanism and propose a novel algorithm: Differentially Private Selective Release based on Clipped Gradients (DPSR-CG). Through a rigorous, newly derived privacy analysis and extensive experiments on multiple datasets (MNIST, CIFAR-10, IMDB, and FMNIST), we demonstrate that our DPSR-CG mechanism maintains strict privacy guarantees while achieving exceptional model performance.

Differentially private stochastic gradient descent (DP-SGD) injects noise into every updated coordinate, making the injected noise energy scale with the ambient parameter dimension $d$. We ask when private training can update fewer coordinates without losing the signal needed for optimization. We propose \textsc{TP-TopK} (Two-Phase TopK DP-SGD), a two-phase method for coordinate-sparse private training without public data, in which a private warm-up phase identifies a coordinate support used to guide the main training phase. We give a criterion characterizing when coordinate restriction can be beneficial, show via a nonconvex stationarity bound that under this condition the relevant noise term scales with the active dimension $k$ rather than the full parameter dimension $d$, and provide a lower bound on the reliability of warm-up-based coordinate ranking. Experiments on MNIST, FMNIST, and CIFAR-10 show that learned coordinate supports can retain more gradient energy than size-matched random supports, with the largest gains when the active dimension is small and warm-up scores are informative.

We study the robustness of stochastic mirror descent (SMD) under heavy-tailed noise, focusing on whether the method retains its convergence guarantees when run with infinite-variance stochastic gradient input. To address this question in a principled manner, we begin by introducing a continuous-time model of SMD as a stochastic differential equation (SDE) driven by a centered Lévy noise process with finite $p$-th order moments, $1 < p \leq 2$. This scheme -- which we call the Lévy mirror flow (LMF) -- arises naturally as the scaling limit of SMD in the presence of heavy-tailed noise. In particular, when $p < 2$ -- the heavy noise regime -- the trajectories of LMF generically exhibit jump discontinuities of arbitrary magnitude which, if frequent enough, lead to infinite variance. Nonetheless, despite this highly singular behavior, we show that LMF attains $ε$-optimality within $\mathcal{O}(ε^{-p/(p-1)})$ time in the convex case, and within $\mathcal{\tilde O}(ε^{-1/(p-1)})$ time for (relatively) strongly convex objectives. These guarantees provide a transparent characterization of the impact of frequent long jumps on the convergence of the process, and percolate to a series of matching discrete-time guarantees for several variants of SMD under heavy-tailed noise.

Training modern machine learning models increasingly requires computation to be distributed across many accelerators. Data parallelism remains the default choice and is often paired with tensor-parallel sharding, but model parallelism becomes unavoidable once parameters, activations, or optimizer states no longer fit on a single device. This paper studies pipeline model parallelism through the lens of PipeDream (PD) (Harlap et al., 2018). Our first contribution is theoretical: we introduce Randomized PipeDream (RPD), a stale block-SGD abstraction that yields, to our knowledge, the first clean nonconvex convergence guarantee for a PD-style method. Our second contribution is a scaling diagnosis: we prove that the delay induced by steady-state PD grows as $S^2 - S/2 + O(1)$ for $S$ stages, so the stale-read contribution in the convergence theorem scales as $Θ(γ^2 S^4)$, equivalently as $Θ(S^4/K)$ in the tuned-rate form. Our third contribution is a comparison with LocalSGD, whose periodic model averaging trades weight staleness for synchronization bubbles. In our reported simulated-time experiments, the better-performing method depends on the objective: PD performs better on the quadratic objective and on a small language-modeling training-loss task, while for logistic regression LocalSGD becomes superior as the number of stages increases.

The existing optimizers for deep neural networks (DNNs) typically rely on either the $\ell_2$ norm or the $\ell_\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong curvature anisotropy in the early period, whereas in the later period, the training process of DNNs tends to move toward flatter regions with weaker anisotropy. Particularly, optimizers based on the $\ell_2$-norm are usually dominated by high-curvature directions, restricting updates of optimizers along with lower curvature direction and thus leading to a slower convergence rate. While optimizers based on the $\ell_\infty$-norm are prone to oscillations in flatter regions, due to the coordinate-wise updates of the same magnitude. To address these two extreme cases generated by $\ell_2$ and $\ell_\infty$ norms, we propose a novel $\ell_p$-norm scheme with a dynamical value of $p$ and incorporate it into stochastic gradient descent (SGD) and SGD with momentum (SGDM), leading to two novel optimizers with better generalization performance: ${\ell_p}$-SGD (LPSGD) and ${\ell_p}$-SGDM (LPSGDM). Particularly, the resulting optimizers suppress the dominance of high-curvature directions in the early period by utilizing a large $p$ ($p>2$), followed by a gradual decrease of $p$ toward 2 to enable more stable and refined updates, where the latter process is motivated by the cosine annealing strategy. We establish theoretical guarantees of the resulting algorithms and analyze that both LPSGD and LPSGDM achieve an $O(T^{-1/2})$ convergence rate for the nonconvex setting. Extensive experiments are conducted on benchmark datasets, including CIFAR-10, CIFAR-100, and ImageNet-1K, with multiple DNNs such as VGG-11, ResNet-18, and ResNet-50.

Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of the loss landscape, SAM often improves generalization while delivering strong empirical performance. However, SAM and its variants, like most training algorithms, are sensitive to the choice of learning rate, which is typically selected through extensive hyperparameter tuning or predefined schedulers. In this work, motivated by recent advances on the effectiveness of stochastic Polyak step sizes for Stochastic Gradient Descent (SGD), we derive Polyak schedulers tailored to SAM-style updates, yielding novel adaptive algorithms in both deterministic and stochastic settings. In the smooth setting, we prove linear convergence for strongly convex objectives and an $\mathcal{O}(1/T)$ convergence rate for convex objectives in the deterministic case. In the stochastic setting, we establish analogous convergence guarantees up to a neighborhood of the optimum. Numerical experiments demonstrate that the proposed Polyak schedulers achieve performance comparable to or better than carefully tuned SAM baselines, while substantially reducing the need for learning-rate tuning.

Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization. While existing studies offer isolated insights, a unified theoretical framework explaining the efficacy of KT across these disparate regimes remains lacking. In this work, we establish a unified spectral analysis of SGD dynamics in high-dimensional linear regression, elucidating the efficiency of KT across seemingly disparate regimes. We characterize KT efficiency through two distinct mechanisms: \emph{Spectral Horizon Expansion} in KD, which enables the capture of statistically inaccessible high-frequency signals, and \emph{Spectral Denoising} in W2S, where the student acts as a filter for optimization noise. Our framework unifies these phenomena, revealing that the efficacy of transfer is governed by the interplay between implicit regularization and heterogeneous spectral learning speeds over the spectrum.

Many stochastic gradient methods are believed not to converge when the noise in stochastic gradients has only a finite $p$-th moment for $p\in\left(1,2\right)$, a setting known as the heavy-tailed noise assumption. However, some recent studies have found that Stochastic Gradient Descent ($\textsf{SGD}$), without any modification to its update rule, can surprisingly converge in expectation for convex problems with bounded domains, highlighting the potential of classical stochastic gradient methods. Inspired by this recent progress, we provide a comprehensive study of stochastic optimization under heavy-tailed noise and establish new in-expectation convergence results for Stochastic Mirror Descent ($\textsf{SMD}$) and Accelerated Stochastic Mirror Descent ($\textsf{ASMD}$) in convex optimization, and for $\textsf{SGD}$ and Stochastic Gradient Descent with Momentum ($\textsf{SGDM}$) in nonconvex optimization. Notably, our results not only hold without algorithmic changes but also avoid restrictive assumptions, such as bounded domains, imposed in prior work. More importantly, our analysis provides a new, elegant, and powerful framework for studying heavy-tailed stochastic optimization, opening a new route to understanding first-order stochastic gradient methods.

Tuning algorithms such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challenging, particularly in the practically relevant settings when the batch size is large or the model is misspecified. Existing theory that provides tuning guidance relies on continuous-time limits or strong statistical assumptions, which can become quantitatively inaccurate in these regimes. We address these shortcomings by proposing new discrete-time approximations to SG(L)D with and without momentum, which enables accurate predictions of the stationary covariance, iterate average covariance, and integrated autocorrelation time. Moreover, we prove quantitative, non-asymptotic error bounds showing that these estimates are sufficiently accurate for practical tuning and uncertainty quantification. Numerical experiments demonstrate that our theory yields improved tuning guidance across a range of models and data-generating distributions where existing approaches fail, including when using the $β$-divergence rather than log-loss to obtain statistically robust inferences.

Existing theory of momentum assumes that gradients arrive at every parameter at a roughly constant rate, an assumption violated in practice by heavy-tailed data distributions and modern architectures. We theoretically analyze the dynamics of two tractable models of momentum under sparse updates: a least squares model with sparse inputs and a logistic regression model with a rare class. Both admit exact closed-form second-moment dynamics whose high-dimensional limits we characterize across three scaling exponents for sparsity, batch size, and momentum decay. The phase structure on both problems is governed by the ratio of two intrinsic timescales: a momentum retention timescale (how many active updates the buffer survives) and a learning timescale (how many active updates it takes to reduce the squared error). When learning is much slower than retention, the limit matches SGD; when learning is faster, the system is unstable; where the timescales coincide, we recover classical heavy-ball dynamics. The oscillatory dynamics occur at different momentum values for different token sparsity, creating a spectral conflict for global momentum across token frequencies.

Stochastic gradient descent with momentum (SGDM) is one of the most widely used optimization algorithms in machine learning. While optimization properties of SGDM have been extensively studied in the literature, it remains insufficiently understood whether and when SGDM can generalize well to unseen data. In particular, it has been conjectured that while momentum accelerates training, it may degrade generalization. In this paper, we close this gap by developing a comprehensive generalization analysis of SGDM through the lens of algorithmic stability. More specifically, we introduce a generalized SGDM framework that encompasses both Polyak's and Nesterov's momentum schemes, and establish tight on-average model stability bounds for smooth and convex problems. Notably, the obtained bounds exploit small optimization error bounds along the trajectory, apply to any momentum parameter in the interval $[0, 1)$, and do not require the commonly assumed Lipschitzness of loss functions. We further derive optimization error bounds for the generalized SGDM, and combine them with our generalization analyses to obtain optimal excess population risk bounds for SGDM with both Polyak's and Nesterov's momentum.

Deep neural network training often exhibits highly anisotropic loss geometry, where a few sharp dominant Hessian directions coexist with a large flatter bulk. Gradients tend to align disproportionately with these dominant directions, although stable progress often requires movement through flatter bulk directions. Estimating the dominant subspace is therefore useful but costly with direct Hessian-based methods. We show that standard Local SGD exposes this geometry through worker disagreement. We theoretically show that the worker-average gap covariance is shaped by stochastic-gradient noise and Hessian curvature, causing workers to disagree along sharp, curvature-sensitive directions. Thus, worker-average gaps provide a cheap Hessian-free estimator of the dominant subspace. Experiments on MLPs, CNNs, and Transformers show that subspaces formed by worker-average gaps capture a substantial fraction of the gradient component lying in the dominant Hessian eigenspace.

Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the underlying min-max objective is optimized. In practice, Stochastic Gradient Descent (SGD) optimizer remains the default optimization choice for AT, whereas adaptive optimizers often improve standard training but may yield inferior robustness. Recently, the Muon optimizer, which orthogonalizes matrix-valued updates via an approximate polar decomposition, has achieved notable success in large-scale training at a memory cost comparable to SGD. This raises a security-relevant question: \textit{can orthogonalized optimization improve AT under strong and heterogeneous threat models?} Focusing on this problem, we conduct a comprehensive theoretical and empirical study. Theoretically, we show that Muon imposes a spectral-norm stability ceiling on matrix updates, limiting uncontrolled spectral growth in the training dynamics without explicitly shrinking the learned weights. Empirically, across five architectures and three $\ell_p$ threat models ($\ell_\infty$, $\ell_1$, $\ell_2$) and their union, Muon is competitive with SGD on CNNs and substantially outperforms AdamW on both CNNs and ViTs. These results identify optimizer geometry as a security-relevant factor in adversarial training, while clarifying the empirical regimes in which orthogonalized updates are beneficial. Overall, our findings highlight optimizer design as a security-critical component of AT.

Understanding the relationship between generalization and privacy remains a central challenge in modern machine learning theory, particularly for deep networks trained by variants of differentially private stochastic gradient descent (DP-SGD). In this work we make progress on this persistent open problem by proving a finite-sample bound on the approximate max-information of DP-SGD that exhibits scaling properties comparable with (Dwork et al, 2015)'s classic result for $ε$-differentially private algorithms, namely at most linear in the dataset size. From our result we obtain a general-purpose PAC-Bayes generalization bound in which the necessary prior distribution can be learned by DP-SGD, as well as a generalization bound for DP-SGD-trained models themselves, with a complexity term that is fully explicit and controlled by the optimization hyperparameters.

Stochastic gradient descent (SGD) is a foundational algorithm for large-scale statistical learning and stochastic optimization. However, statistical inference based on SGD iterates remains challenging when stochastic gradients have infinite variance, as the relevant limiting distributions depend on unknown nuisance parameters. In this paper, we develop an efficient, model-agnostic methodology for constructing confidence regions from SGD trajectories that applies in both finite- and infinite-variance regimes. The procedure is based on a joint weak convergence result for the Polyak-Ruppert averaged estimator and an empirical second-moment normalizer constructed from stochastic gradients along the SGD trajectory. This joint limit yields a self-normalized statistic in which the leading tail-dependent scaling terms cancel. We then use a subsampling calibration scheme to estimate the relevant critical values, avoiding explicit estimation of tail indices, slowly varying functions, or stable-law parameters. The resulting confidence regions are straightforward to implement and are asymptotically valid under both the finite- and infinite-second-moment regimes. Simulation studies show reliable coverage in various settings, supporting the proposed method as a practical tool for uncertainty quantification in stochastic optimization.

Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, provides a principled framework for training LLMs with provable privacy protection. However, state-of-the-art DP training implementations rely on fast gradient clipping techniques with memory overhead $O(B \min\{T^2, d^2\})$, where $B$ is the batch size, $T$ is the sequence length, and $d$ is the model width. This becomes prohibitive as both model size and context length grow. We propose DP-SGD-RC, a novel variant of DP-SGD with randomized clipping that reduces memory and compute complexity. DP-SGD-RC leverages stochastic trace estimation methods, specifically Hutchinson's estimator[Hutchinson, 1989] and its improved variant, Hutch++[Meyer et al., 2021], to reduce the memory footprint of per-sample gradient norm estimation. We provide a tight privacy analysis showing that DP-SGD-RC achieves noise multipliers competitive with deterministic clipping. Experiments fine-tuning Llama~3.2-1B on long-context benchmarks spanning classification, question answering, and summarization tasks demonstrate that DP-SGD-RC matches baseline utility while significantly reducing memory and compute requirements.

Scaling laws provide compact descriptions of how prediction error varies with compute, model size, and data, but existing theory mainly treats single-sample SGD or full data reuse, leaving the role of mini-batching unclear. We study batch scaling laws for sketched linear regression under a power-law covariance spectrum and a source condition on the target parameter. We analyze one-pass batch SGD, multi-pass batch SGD with replacement, and multi-pass batch SGD without replacement. Our first result is a risk decomposition: all three procedures share the same irreducible and approximation terms, while their stochastic terms depend on the sampling protocol. One-pass batch SGD splits into bias and variance, whereas the two multi-pass methods split into GD bias, GD variance, and a fluctuation term around a common GD reference trajectory. We then prove source-condition scaling laws for one-pass and multi-pass mini-batch methods. For one-pass batch SGD, mini-batching preserves the approximation and optimization-bias exponents, while the variance scales as $O(\min(M,(T_{\mathrm{eff}}γ)^{1/a})/(B T_{\mathrm{eff}}))$. Thus the usual $1/B$ covariance reduction holds at fixed update count $T$, but in the one-pass regime $T=N/B$ it is partly offset by the shorter optimization horizon. For multi-pass batch SGD, with- and without-replacement sampling have identical approximation and GD bias/variance terms; they differ only in the fluctuation covariance prefactor, which is $1/B$ with replacement and $ρ_{N,B}=(N-B)/(B(N-1))$ without replacement. Hence without-replacement sampling is less noisy for $B>1$, and when $B=N$ the fluctuation vanishes, recovering deterministic gradient descent. These results place batch size on the same theoretical footing as compute, data, and model dimension in sketched linear regression.

Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not match the discrete SGD update at finite learning rate. In this work, we propose an alternative formulation of SGD as deterministic dynamics in a fluctuating loss landscape induced by minibatch sampling. Starting directly from the discrete update, we derive a master equation for the parameter distribution and obtain a discrete Fokker--Planck equation that differs from the standard Langevin form at order eta^2. Using this framework, we analyze SGD dynamics near critical points of the loss. We show that the behavior decomposes along the eigenbasis of the mean Hessian into qualitatively distinct regimes. In particular, nearly-flat directions do not admit a stationary distribution: the variance grows over time, corresponding to effective diffusion along valleys with a coefficient proportional to the learning rate. We provide empirical evidence supporting these predictions on neural network models in computer vision and natural language processing, observing a clear qualitative separation between confined and diffusive modes.

Communication is a major bottleneck in distributed learning, especially in large-scale settings and in federated learning environments with slow links. Three standard ways to reduce this cost are communication compression, local training, and communication-computation overlap. Methods that combine these ingredients are used in practice and have been found to be effective for large-scale training, but there is little theory for methods that combine all three. We study a heterogeneous-compute setting in which different workers may take different numbers of local steps, and we propose LOSCAR-SGD, a Local SGD method that communicates only a sparse subset of model coordinates and continues optimizing while communication is in flight. A key ingredient is a delay-corrected merge rule that incorporates delayed synchronized information without discarding the progress made during the overlap phase. We give convergence guarantees for smooth non-convex objectives and show how sparsity, overlap, and worker heterogeneity affect the rate. To the best of our knowledge, this is the first theory for this combination of ingredients. Experiments further show that communication-computation overlap reduces training time and that the delay-corrected merge outperforms naive overwriting.

Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, but its high-variance updates can reduce utility on challenging datasets. We propose \textbf{SMA-DP-SGD}, a \textbf{Spectral Memory-Aware Differentially Private Stochastic Gradient Descent} method that augments DP-SGD with a fractional memory branch built only from previously privatized noisy releases. WeightWatcher-inspired power-law spectral exponents provide group-wise reliability signals, instantiated layer-wise in our experiments, to adapt the decay and effective memory depth. Private-history alignment, norm matching, and warm-up activation stabilize the memory contribution. Privacy remains transparent: conditioned on the private release history, the memory branch is fixed, and the only newly data-dependent term is the current clipped sum scaled by a fixed coefficient $β$. Hence, SMA-DP-SGD preserves a clean conditional sensitivity structure and exactly recovers group-wise DP-SGD when $β=1$. Experiments on CIFAR-100, CIFAR-10, and MNIST show competitive or superior accuracy over several DP optimization baselines, with the largest gains on CIFAR-100 and CIFAR-10. CIFAR-10 ablations show that $β$ controls the privacy--utility trajectory, while spectral and memory diagnostics confirm a controlled short-to-moderate effective memory depth and a small memory-branch ratio. Runtime analysis shows that the mechanism incurs additional overhead, about $2.94\times$ DP-SGD in our CIFAR-10 implementation, revealing a practical trade-off between adaptive private memory and computational cost.

Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such methods to achieve significant breakthroughs. To achieve such an effect, we first analyze the issue of "high-loss non-adversarial examples" that degrades attack performance in previous methods, and prove that this issue arises from inappropriate objectives for adversarial example generation. Subsequently, we reconstruct the objective as "maximizing the difference between the non-ground-truth label probability upper bound and the ground-truth label probability", and proposes a novel and powerful gradient-based attack method named Sequential Difference Maximization (SDM). SDM establishes a three-layer optimization framework of "cycle-stage-step". It adopts the negative probability loss function and the Directional Probability Difference Ratio (DPDR) loss function in the initial and subsequent optimization stages, respectively, and approaches the ideal objective of adversarial example generation via stage-wise sequential optimization. Experiments demonstrate that compared with previous state-of-the-art methods, SDM not only achieves stronger attack performance but also exhibits superior cost-effectiveness. The code is available at https://github.com/X-L-Liu/ICML-SDM.

Backpropagation with gradient descent is a common optimization strategy employed by most neural network architectures in machine learning. However, finding optimal hyperparameters to guide training has proven challenging. While it is widely acknowledged that selecting appropriate parameters is crucial for avoiding overfitting and achieving unbiased outcomes, this choice remains largely based on empirical experiments and experience. This paper presents a new probabilistic framework for the learning rate, a key parameter in stochastic gradient descent. The framework develops classic Bayesian statistics into a double-Bayesian decision mechanism involving two antagonistic Bayesian processes. A theoretically optimal learning rate can be derived from these two processes and used for stochastic gradient descent. Experiments across various classification, segmentation, and detection tasks corroborate the practical significance of the theoretically derived learning rate. The paper also discusses the ramifications of the proposed double-Bayesian framework for network training and model performance.

Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory. However, all current methods impose fixed LMO geometries for the update rules, chosen by-design or empirically, which are not necessarily optimal according to the problem's geometry. We introduce a novel efficient datadriven criterion for dynamically choosing proxy-optimal update LMO geometries on individual Deep Neural Network layers. Derived in closed form from gradient and activation statistics using a single-step random feature regression surrogate model, our criterion navigates a design space interpolating from SGD to Muon updates. Moreover, integrating parameter-wise preconditioning allows our framework to recover SGD, Muon, Adam, and MuAdam as specific extrema. To make this adaptive approach scalable, we pair it with efficient computational strategies, achieving only a $\sim$ 3% runtime overhead on highly optimized baselines. As a proof of concept, we show that this data-driven optimizer beats or remains competitive with the performance of the best performing optimizer between Muon and AdamW across three different training scenarios. Ultimately, this work provides evidence that LMO geometry can be successfully and efficiently adapted from runtime data, opening a new pathway for optimizer design beyond static geometries.

Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation schemes generally introduce systematic gradient biases, as shown for linear models. In this work, we prove that all parametric models exhibit similar gradient bias for various imputation procedures and characterize exactly the dependence on the missingness ratio vector $p$, with $O(\|p\|)$ as the leading term. We exploit this analysis to propose a simple debiasing procedure for stochastic gradient descent (SGD) with missing values based on Richardson extrapolation, which leverages the exact expression of the gradient bias. The key idea is to \emph{deliberately add missingness}: from an already incomplete observation, we generate a further-thinned version at a higher, controlled missingness level, and combine the two resulting stochastic gradients to cancel the leading bias term. We prove that one Richardson step reduces the gradient bias from $O(\|p\|)$ to $O(\|p\|^2)$ under several missingness scenarios. Our proposed method is computationally efficient, model-agnostic and applies to any parametric loss whose stochastic gradient can be computed after imputation. Furthermore, when missing indicators are independent, the population gradient bias is a multilinear polynomial in $p$ and depends only on population gradient errors induced by declaring a single coordinate missing. In this case, our method generalizes to a multi-step Richardson procedure which recursively cancels higher-order terms. Empirically, Richardson debiasing improves optimization and estimation across several generalized linear models and combines positively with widely used imputation procedures such as MICE. These results suggest that, somewhat counter-intuitively, adding controlled missingness on top of existing missing data can make stochastic learning from incomplete data more accurate.

Using recent works of one of the authors (VSB) on collapse in generative models and two time scale dynamics in stochastic gradient descent in high dimensions, we give a system theoretic explanation of the memorization phenomenon in generative models. This relies purely on the dynamic aspects of the training phase. Specifically, we use a result of Austin [2016] to motivate a stylized model for the loss function for stochastic gradient descent (SGD) wherein the loss function has a strong dependence on some variables and weak dependence on the rest in a precise sense. This naturally leads to two distinct time scales in the constant step size SGD that is commonly used in machine learning. This fact has been used to explain the double descent phenomenon in SGD in Borkar [2026]. In conjunction with a mathematical model for collapse phenomenon in SGD developed in Borkar [2025a], we analyze the constant step size SGD using the recent results of Azizian et al. [2024] in order to explain the phenomenon of memorization wherein a generative model that is concurrently being tuned yields the same or similar outputs for significant stretches of time. This gives a novel perspective on the aforementioned phenomena reported in machine learning literature and their interrelationships, using a dynamical systems viewpoint.

The global deployment of edge intelligence operates across heterogeneous legal frameworks. While some regions permit centralized learning (CL) via cloud data aggregation, others enforce strict data localization, necessitating federated learning (FL). This operational dichotomy introduces two incompatible optimization regimes (i.e., unbiased global gradients yet coupled with internal covariate shift in CL versus biased, drift-prone local updates in FL), resulting in that any naive integration of the two lacks rigorous theoretical guarantees. To fill this gap, we propose OmniISR, a unified framework that fuses pure CL, pure FL, and hybrid CL-FL training modes via equipping intermediate supervision and regularization (ISR) signals at multiple hidden layers. Specifically, we propose (i) to use mutual-information (MI) as intermediate supervision to align shifting internal covariate in CL and client-drifting representations in FL, and (ii) to adopt negative-entropy (NE) as intermediate regularizer to penalize overconfident prediction, preserve representational uncertainty, and avoid device-specific collapse. On the theory side, we derive (i) a unified, ISR-agnostic, and non-asymptotic O(1/sqrt(T)) convergence bound that shows the introduced ISR does not violate standard SGD convergence, (ii) a federated drift-bound that quantifies the ISR-reduced client drift, (iii) a gradient-alignment guarantee that ensures non-conflicting CL and FL updates under mild bias, and (iv) an explicit escape-time bound that indicates that CL-FL hybrid mixing enlarges effective stochasticity and accelerates escape from strict saddles. Extensive experiments demonstrate that OmniISR consistently improves model performance in both centralized and federated paradigms, reduces the CL-FL gap by 22.60%, and yields 37/48 paired metric wins across multiple FL algorithms.

Stochastic gradient descent (SGD) is a fundamental optimization algorithm widely used in modern machine learning. In this paper, we propose Factor-Augmented SGD (FSGD), a new optimization method that leverages latent factor representations in high-dimensional learning tasks. Unlike standard two-stage dimension reduction approaches that rely on offline representation learning and full data storage, a key novelty of FSGD is that it operates purely on streaming data, making it scalable to large-scale and high-dimensional problems. Furthermore, we establish the first theoretical framework that explicitly incorporates latent factor estimation error into the analysis of SGD, and provide moment convergence in $\ell^s$ norm under decaying step sizes and mini-batch updates. Our results provide a new foundation for employing SGD reliably and scalably in high-dimensional machine learning systems.

Lagrangian Relaxation (LR) is a powerful technique for solving large-scale Mixed Integer Linear Programming (MILP), particularly those with decomposable structures, such as vehicle routing or unit commitment problems. By relaxing the coupling constraints, LR enables parallel subproblem solving and often yields tighter dual bounds than standard linear programming relaxations, which is crucial for efficient branch-and-bound pruning. While recent empirical work has shown promising results using machine learning to predict these multipliers, a theoretical understanding of such methods remains an open question. In this work, we bridge this gap by analyzing the problem of learning LR through the lens of Data-driven Algorithm Design, i.e., a statistical learning problem over a distribution of problem instances. Our contributions are as follows: first, we derive a generalization bound of $\mathcal{O}(s^{1.5}/\sqrt{N})$ for the learned multipliers, where $s$ is the number of coupling constraints and $N$ is the sample size. Second, we provide a minimax lower-bound of $Ω(s/\sqrt{N})$, proving that a linear dependency is unavoidable. Third, we constructively close this theoretical gap by proving that Stochastic Gradient Ascent (SGA) with averaging achieves the minimax optimal rate $Θ(s/\sqrt{N})$. Finally, we extend our framework to the learning-to-warm-start setting, proving that it achieves a fast, minimax-optimal rate of $Θ(s/N)$ and establishing a theoretical advantage over direct multiplier prediction.

Accelerating stochastic gradient methods with classical momentum schemes, such as Polyak's heavy ball, has proven highly successful in training large-scale machine learning models, particularly when combined with the hardware acceleration of large mini-batch computations. Yet, the effect of classical momentum on stochastic mini-batch optimization has been poorly understood theoretically, with prior works requiring strong noise assumptions and extremely large mini-batches. In this work, we develop a general theory of stochastic momentum acceleration for optimizing over quadratics in the interpolation regime, a popular abstraction for studying deep learning dynamics which also includes classical methods such as randomized Kaczmarz and coordinate descent. Our framework encompasses both heavy ball and Nesterov-style momentum, allows for arbitrary mini-batch sizes, and makes minimal assumptions on the stochastic noise. In particular, we show that acceleration from classical momentum is directly proportional to the gradient mini-batch size (up to a natural saturation point), thereby enabling perfect parallelization of mini-batch computations. Our theory also provides a simple choice for the momentum parameter, which is shown to be effective empirically.

A growing lesson from neural network optimization is that optimizer design should respect how the model is parametrized. The layerwise input-output structure of neural networks motivates scale-invariant optimizers, such as Muon and Scion, whose updates also support hyperparameter transfer. At the same time, stochastic gradient noise in deep learning is often far from sub-Gaussian and may exhibit heavy tails. These observations have shaped recent algorithmic principles for training neural networks, yet their joint theoretical consequences are underexplored. In particular, it remains unclear what dimension dependence is unavoidable for gradient-based methods given the problem class is defined by input-output norm and under heavy-tailed noise, and whether higher-order smoothness can accelerate training. We study these questions through nonconvex smooth stochastic optimization over $\mathbb R^{m\times n}$ equipped with general norms and under $p^\mathrm{th}$-moment heavy-tailed noise, where the goal is to achieve an $ε$-stationary point in the dual norm. Our first contribution is a dimension-dependent lower bound: when $\frac{\max\{m,n\}}{(\min\{m,n\})^2}$ is large enough, any gradient-based method requires $Ω(\min\{m, n\}ε^{-\frac{3p-2}{p-1}})$ oracles for the problem class defined by the spectral norm, which is a common input-output norm. We prove that a scale-invariant Scion method with the spectral norm can achieve the matching upper bound of $O(\min\{m, n\}ε^{-\frac{3p-2}{p-1}})$. To exploit higher-order smoothness, we propose a transported Scion method and improve the bound to $O(\min\{m, n\}ε^{-\frac{5p-3}{2p-2}})$ when the Hessian is Lipschitz. Finally, we incorporate heuristics into our transported method and evaluate it across multiple architectures and model sizes, demonstrating its flexibility and compatibility with neural network training.

Optimization problems in real-world applications across the medical and engineering domains often involve potential risks when evaluating candidate solutions. Safe optimization aims to perform optimization while suppressing unsafe solution evaluations in such situations. For continuous search spaces, there exist safe optimization methods based on evolutionary computation. However, the algorithm development of safe optimization methods for binary search spaces has not been adequately addressed. In this study, we incorporate additional mechanisms for safe optimization into a binary optimization method, the adaptive stochastic natural gradient method (ASNG) with a family of Bernoulli distributions. For safety functions that must be kept non-negative during optimization, the proposed method, safe ASNG, estimates the Lipschitz constants with respect to the Hamming distance by constructing surrogate models of safety functions based on discrete Walsh functions. Then, safe ASNG computes a safe region that consists of safe solutions around the previously evaluated safe solutions. By projecting newly generated solutions to their nearest neighbors within the safe region, safe ASNG suppresses unsafe solution evaluations. Experimental results on benchmark problems on binary domains confirm that, while the comparative methods fail to suppress unsafe solution evaluations, safe ASNG achieves efficient optimization while effectively suppressing unsafe solution evaluations.

Understanding the behavior of stochastic gradient methods is a central problem in modern machine learning. Recent work has highlighted diagonal linear networks as a simplified yet expressive setting for analyzing the optimization and generalization properties of neural models. In this work, we show that in the high-dimensional regime, stochastic gradient descent on diagonal linear networks is well-approximated by continuous dynamics governed by a stochastic differential equation (SDE), which explicitly decouples the drift from the gradient noise. We further derive a deterministic partial differential equation whose solution propagates the relevant state of the iterates and characterizes the time evolution of a broad class of observable statistics, including the risk, curvature, and other metrics for optimality. Finally, we show that, under a suitable parametrization, the stochastic dynamics are globally well posed and converge exponentially fast to zero risk with high probability, yielding a fully explicit non-asymptotic description of their long-time behavior. Numerical simulations corroborate our theoretical findings.

We study nonconvex stochastic optimization under the Blum-Gladyshev ($\mathsf{BG}$-0) noise model, where the stochastic gradient variance grows quadratically with the distance from the initialization. We consider this problem under both standard smoothness and the symmetric generalized-smoothness framework, which captures objectives whose local curvature can scale with the gradient norm. We prove that normalized stochastic gradient descent with momentum, using only one stochastic gradient per iteration, converges under $\mathsf{BG}$-0 noise with oracle complexity $O(\varepsilon^{-6})$. This rate holds both for standard smoothness and for $α$-symmetric generalized smoothness, showing that generalized smoothness is rate-neutral for normalized momentum in this setting. We then study a variance-reduced normalized STORM method. Under mean-square smoothness and sharp initialization, the method achieves the minimax optimal $O(\varepsilon^{-4})$ complexity, matching the lower bound. Under expected $α$-symmetric generalized smoothness, the STORM recursion couples gradient-dependent smoothness with distance-dependent noise, leading to complexity $O(\varepsilon^{-(4+α)})$ for $α\in(0,1)$ and $O(\varepsilon^{-5})$ for $α=1$. When the distance-growth parameter in the noise model vanishes, our guarantees recover the standard bounded-variance rates: $O(\varepsilon^{-4})$ for momentum, $O(\varepsilon^{-3})$ for variance reduction, and $O(\varepsilon^{-2})$ in the deterministic case. To our knowledge, these are the first convergence guarantees for normalized methods in non-convex stochastic optimization under $\mathsf{BG}$-0 noise without bounded domains, increasing batch sizes, or explicit anchoring, covering both standard and generalized smoothness regimes.

Asynchronous stochastic gradient descent (ASGD) is a standard way to exploit heterogeneous compute resources in distributed learning: instead of forcing fast workers to wait for slow ones, the server updates the model whenever a gradient arrives. Vanilla ASGD applies each arriving gradient with the same weight. When local data distributions are heterogeneous, this becomes problematic: faster workers contribute more updates, and we show theoretically that the method is biased toward a frequency-weighted average of the local objectives rather than the desired global objective. Existing remedies typically move away from the simple ASGD template by introducing gathering phases, buffering, or extra memory. We show that this is unnecessary. Keeping the standard ASGD mechanism, we recover the correct objective by rescaling worker-specific stepsizes in proportion to their computation times, so that each worker contributes the same aggregate learning rate over a cycle. In the non-convex setting, under smoothness and bounded heterogeneity assumptions, we prove that the resulting method, Rescaled ASGD, converges to stationary points of the correct global objective in the fixed-computation model. Its time complexity matches the known lower bound in the leading term, while the effects of staleness and data heterogeneity appear only in lower-order terms. Experiments confirm that the method converges to the correct objective and is competitive with state-of-the-art baselines.

Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing theoretical analyses either fix the student's representations or operate in restricted settings. Whether multi-step SGD can succeed in feature learning while preserving diverse pre-trained capabilities remains open. We study W2S in the setting of reward-model learning with two-layer neural networks. The strong model has pre-trained representations organized into low-dimensional subspaces $V_k$, and is fine-tuned under the supervision of a weak model specialized on task $κ$. We prove that the strong model efficiently learns task $κ$, eliciting its pre-trained knowledge while retaining general capabilities. This establishes W2S generalization in the feature-learning regime, in the sense that the strong model acquires the target feature direction through W2S training, rather than having it given a priori. Moreover, W2S preserves pre-trained off-target features, whereas standard supervised fine-tuning causes catastrophic forgetting when off-target feature directions are correlated with the target's. Numerical experiments on synthetic data confirm our theoretical results.

We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise. This setting is substantially closer to practice than prior KAN theory along two axes: training is by mini-batch SGD, the standard recipe for modern networks, rather than full-batch gradient descent (GD); and correlated-noise mechanisms have empirically shown a more favorable privacy-utility tradeoff than independent-noise mechanisms. Our results cover the corresponding full-batch GD and independent-noise DP-GD results for KANs by Wang et al. (2026), while yielding sharper fixed-second-layer specializations. The technical core is a new analysis route for correlated-noise DP training in the non-convex regime. Temporal dependence breaks the conditional-centering structure underlying standard one-step SGD arguments, and the projection step obstructs the exact cancellation structure of correlated perturbations. We address these difficulties through an auxiliary unprojected dynamics, a shifted iterate that absorbs the current noise perturbation, and a high-probability bootstrap certifying projection inactivity. Combining this optimization analysis with a stability-based generalization argument yields the stated population risk bounds. To the best of our knowledge, this is the first optimization and population risk analysis of a correlated-noise mechanism for DP training beyond convex learning, in particular for neural networks.

Federated learning (FL) enables the collaborative training of large-scale language models (LLMs) across edge devices while keeping user data on-device. However, FL still exposes sensitive information through client-provided gradients. Differentially private stochastic gradient descent (DP-SGD) mitigates this risk by clipping each client's contribution to a threshold $C$ and adding noise proportional to $C$. Existing adaptive clipping techniques dynamically adjust $C$ but demand tedious hyperparameter tuning, which can erode the privacy budget. In this paper, we introduce DP-LAC, a method that first estimates an initial clipping threshold within an order of magnitude of the optimum using private histogram estimation, and then adapts this threshold during training without consuming additional privacy budget or introducing new hyperparameters. Empirical results show that DP-LAC outperforms both state-of-the-art adaptive clipping methods and vanilla DP-SGD, achieving an average accuracy gain of $6.6\%$.

We study how temporal correlations in the data can make certain sparse learning problems efficiently learnable by gradient-based methods. Our focus is on Boolean k-juntas, a canonical sparse learning problem known to pose barriers for gradient-based methods under independent uniform samples. We show that this picture changes when the samples are generated by a lazy random walk on the hypercube. In this setting, the temporal dependencies can be exploited by a two-layer ReLU network trained using stylized-SGD with a temporal-difference loss, which compares target and predicted increments across consecutive samples. For every fixed k, the resulting sample complexity is essentially linear in the ambient dimension d. By contrast, we show that for large-batch gradient methods using standard convex pointwise losses, temporal correlations do not provide the same advantage.

Decentralized stochastic gradient descent (D-SGD) is an efficient method for large-scale distributed learning. Existing generalization studies mainly address expected results, achieving rates limited to $\mathcal{O}\left(\frac{1}{δ\sqrt{mn}}\right)$, where $δ$ is the confidence parameter, $m$ the number of workers, and $n$ the sample size. When $m=1$, D-SGD reduces to traditional SGD, whose optimal high-probability generalization bound is $\mathcal{O}\left(\frac{1}{\sqrt{n}}\log (1/δ)\right)$. This discrepancy reveals a gap between high-probability guarantees for SGD and those for D-SGD. To close this, we develop a high-probability learning theory for D-SGD, aiming for the optimal $\mathcal{O}\left(\frac{1}{\sqrt{mn}}\log (1/δ)\right)$ rate. We refine bounds for D-SGD using pointwise uniform stability in distributed learning-a weaker notion than uniform stability-and analyze them across convex, strongly convex, and non-convex settings. We also provide high-probability results for gradient-based measures in non-convex cases where only local minima exist, and derive optimization error and excess risk bounds. Finally, accounting for communication overhead, we analyze generalization bounds for local models within time-varying frameworks.

Differentially private stochastic gradient descent (DP-SGD) is a standard approach to privacy-preserving learning based on per-example clipping, subsampling, Gaussian perturbation, and privacy accounting. Classical DP-SGD releases a noisy version of the current clipped subsampled gradient sum. We propose Fractional-Order Differentially Private Stochastic Gradient Descent (\textbf{FO-DP-SGD}), a mechanism-level extension that replaces this current-only query, before Gaussian noise is added, with a fractional recursive query combining the current clipped sum with a finite-window, power-law-weighted aggregation of previously released private sum-level outputs. This injects fractional memory into the release mechanism while preserving the standard \emph{sum-then-noise-then-divide} structure. Under add/remove adjacency with Poisson subsampling, the current-step sensitivity analysis shows that the only newly data-dependent term is the scaled current clipped sum. Hence, conditioned on the private history, the effective $\ell_2$-sensitivity is at most $βC$, where $C$ is the clipping threshold and $β\in(0,1]$ controls the current-step contribution. Thus, FO-DP-SGD admits standard per-step Rényi differential privacy accounting via a Poisson-subsampled Gaussian mechanism with effective noise-to-sensitivity ratio $σ/β$, and composes to yield overall $(\varepsilon,δ)$-differential privacy guarantees. FO-DP-SGD provides a framework for studying long-memory effects in private optimization. The fractional order, memory window, and mixing coefficient govern the trade-off among current-step sensitivity, signal retention, and private-history influence. Experiments on SVHN, CIFAR-10, and CIFAR-100 show improved test accuracy and privacy--utility performance over DP-SGD and private baselines including DP-Adam, DP-IS, SA-DP-SGD, ADP-AdamW, DP-SAT, and DP-Adam-AC.

Recently, Muon and related spectral optimizers have demonstrated strong empirical performance as scalable stochastic methods, often outperforming Adam. Yet their behaviour remains poorly understood. We analyze stochastic spectral optimizers, including Muon, on a high-dimensional matrix-valued least squares problem. We derive explicit deterministic dynamics that provide a tractable framework for studying learning behaviour with a focus on (stochastic) SignSVD, which Muon approximates, and (stochastic) SignSGD, the latter serving as a proxy for Adam. Our analysis shows that for large batch size, SignSVD performs a square-root preconditioning with respect to the data covariance spectrum, while for small batch size smaller eigenmodes behave like SGD, slowing down convergence. We contrast with SignSGD which for generic covariance performs no preconditioning and has no transition, leading to different optimal learning rates and convergence characteristics. The two methods match up to a constant factor with isotropic data, but behave differently with anisotropic data. An analysis of a power law covariance model with data exponent $α$ and target exponent $β$ shows there are three phases in the $(α,β)$ plane: one where SignSGD is uniformly favored, one where SignSVD is uniformly favored, and a third where the two methods exhibit a trade-off in performance.

Large-scale machine learning models are trained on clusters of machines that exhibit heterogeneous performance due to hardware variability, network delays, and system-level instabilities. In such environments, time complexity rather than iteration complexity becomes the relevant performance metric for optimization algorithms. Recent work by Tyurin and Richtárik (2023) established the first time complexity analysis for parallel first-order stochastic optimization, proposing Rennala SGD as a time-optimal method for smooth nonconvex optimization. However, Rennala SGD is fundamentally a modification of SGD, and variance reduction techniques are known to improve the iteration complexity of SGD. In this work, we investigate whether variance reduction can also improve time complexity in heterogeneous systems. We show that, under a mean-squared smoothness assumption, variance reduction can improve time complexity in relevant parameter regimes. To this end, we propose Rennala MVR, a variance-reduced extension of Rennala SGD based on momentum-based variance reduction, and analyze its oracle and time complexity. We establish lower bounds for time complexity under these assumptions. On a stochastic quadratic benchmark, experiments with the exact method support the theory, while neural-network experiments with a practical inexact variant show similar empirical gains over Rennala SGD.

Differential privacy (DP) is widely employed in machine learning to protect confidential or sensitive training data from being revealed. As data owners gain greater control over their data due to personal data ownership, they are more likely to set their own privacy requirements, necessitating individualized DP (IDP) to fulfil such requests. In particular, owners of data from more sensitive subsets, such as positive cases of stigmatized diseases, likely set stronger privacy requirements, as leakage of such data could incur more serious societal impact. However, existing IDP algorithms induce a critical utility imbalance problem: Data from owners with stronger privacy requirements may be severely underrepresented in the trained model, resulting in poorer performance on similar data from subsequent users during deployment. In this paper, we analyze this problem and propose the INO-SGD algorithm, which strategically down-weights data within each batch to improve performance on the more private data across all iterations. Notably, our algorithm is specially designed to satisfy IDP, while existing techniques addressing utility imbalance neither satisfy IDP nor can be easily adapted to do so. Lastly, we demonstrate the empirical feasibility of our approach.

Online learning from a stream of data is a defining feature of intelligence, yet modern machine learning systems often struggle in this setting, especially under distributional shift. To understand its basic properties, we study the relationship between online and offline learning in the context of kernel regression. We derive a closed-form expression for the function learned by online kernel regression, revealing that online kernel regression is equivalent to offline regression with shifted, inaccurate target outputs. Conversely, we show that by compensating for this effective shift in the teaching signal through target correction, online kernel-based learning can provably learn the same predictor as its offline counterpart. We derive both a closed-form expression for this target correction and an iterative form that can be applied sequentially. Applying this framework to image classification tasks on CIFAR-10 and CORe50, we show that online stochastic gradient descent with iteratively corrected targets outperforms learning with the true targets in continual learning settings. This work therefore provides a basic framework for analyzing and improving online learning in non-stationary environments.

We consider a first order stochastic optimization framework where, at each iteration, $K$ independent identically distributed (i.i.d.) data point samples are drawn, based on which stochastic gradients can be queried. We allow gradient noise to be heavy-tailed, with possibly infinite variances. For the considered heavy-tailed setting, many algorithmic variants have recently been proposed based on gradient clipping or other nonlinear operators (e.g., normalization) applied over noisy gradients. In this paper, we take an alternative approach and propose a novel stochastic first order method dubbed Robust Stochastic Gradient Descent with medoid mini-batch gradient sampling, R-SGD-Mini for short. The core idea of R-SGD-Mini is to split the $K$-sized data batch into $M$ distinct data chunks, form for each chunk the stochastic gradient, and update the solution estimate with respect to the stochastic gradient direction of the chunk that is medoid of gradients of all data-chunks. Under a general class of symmetric heavy-tailed gradient noises and a standard non-convex setting, we establish explicit bounds on the expected time-averaged squared gradient norm. More precisely, we show that the latter quantity converges at rate $\mathcal{O}(T^{-1})$ to a small neighborhood of zero; we explicitly characterize this neighborhood in terms of noise and algorithm's parameters. Moreover, if the time horizon is known in advance, we establish the rate of $\mathcal{O}(T^{-\frac{1}{2}}).$ Furthermore, when clipping is incorporated, we obtain convergence guaranties in the high-probability sense and recover the same rate. Experimental results indicate that R-SGD-Mini and its clipped variant consistently perform favorably compared to SGD, clipped SGD and Median-of-Means based methods.

Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the stochastic gradients in BBVI inherently exhibit unbounded variance, violating standard assumptions and instead satisfying the weaker Blum-Gladyshev (BG) condition, where variance grows quadratically with distance from the optimum. In this paper, we bridge the gap between stochastic optimization theory and the practical instances of BBVI. Focusing on the broad elliptic location-scale family of parameterized distributions, we offer two main contributions. First, we prove the existence of an ELBO solution, a foundational property usually assumed a priori in the literature. Second, we establish comprehensive convergence guarantees spanning finite-time and asymptotic regimes for Minibatch Projected SGD (PSGD) equipped with dynamic batching and preconditioning under the BG condition. Our theoretical framework demonstrates that dynamic batching combined with preconditioning systematically enables rigorous guarantees even in complex settings. We illustrate our theoretical findings with numerical results, highlighting the efficacy of our approach for modern inference tasks.

Classical optimization theory largely focuses on fixed objective functions, whereas many modern learning systems operate in dynamic environments where data arrive sequentially and decisions must be updated continuously. In this work, we study optimization with streaming data over a distributed network of agents. We adopt a structured, weight-based formulation that explicitly captures the streaming-data origin of the time-varying objective: at each time step, every agent receives a new sample, and the network seeks to track the minimizer of a temporally weighted objective formed from all samples observed across the network so far. We focus on decentralized gradient descent (DGD) with a limited communication/computation budget, where at each time step, only a limited number of DGD iterations can be performed before the objective changes again. For strongly convex and smooth losses, we analyze the tracking error with respect to the time-varying minimizer through a fixed-point theory lens. Our analysis reveals that the tracking error decomposes into a fixed-point tracking term and a bias term induced by data heterogeneity across agents. We specialize the analysis to two natural weighting strategies: uniform weights, which treat all samples equally, and exponentially discounted weights, which geometrically decay the influence of older data. Under uniform weighting, DGD tracks the fixed-point at a rate $\mathcal{O}(1/t)$, whereas discounted weighting yields a non-vanishing fixed-point tracking floor controlled by the discount factor. In both cases, decentralization induces an additional non-zero bias floor under a constant step size. We validate our theoretical findings through numerical simulations.

This paper presents a parametric solution to piecewise linear regression through the Adaptive Block Gradient Descent (ABGD) algorithm. The heart of the method is the parametrization of piecewise linear functions as the difference of max-affine (DoMA) functions. A non-asymptotic local convergence analysis for ABGD is provided under sub-Gaussian covariate and noise distributions. To initialize ABGD, we adapt a prior algorithm originally developed for the simpler setting of max-affine functions. When suitably initialized, ABGD converges linearly to an $ε$-accurate estimate given $\tilde{\mathcal{O}}(d\max(σ_z/ε,1)^2)$ observations where $σ_z^2$ denotes the noise variance. This implies exact recovery given $\tilde{\mathcal{O}}(d)$ samples in the noiseless case. Also, such a rate is shown to be minimax optimal up to logarithmic factors. Synthetic numerical results corroborate the theoretical guarantees for ABGD. We also observe competitive performance compared to the state-of-the-art methods on real-world datasets.