Overview

Grokking studies why a model can fit its training data while performing poorly on new examples, then later generalize, often on tasks such as modular arithmetic, parity, and formal-language recognition. Researchers explain this delay through theories of weight decay, parameter norms, optimization noise, and competing memorization and generalization timescales, alongside analyses of learned circuits and representations using Fourier features, symmetry, and spectral geometry. Experiments also test ways to predict or control the transition, including geometric diagnostics, regularization, architectural changes, and structure-specific priors. A central open question is whether these findings reflect one general mechanism or several task- and optimizer-dependent processes; signals that predict grokking do not always establish its cause.

Latest papers

83 papers7 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Nov 13, 2026

Deep Neural Networks Training Efficiency: Does Grokking Modify its Dynamics?

We study whether grokking, the delayed emergence of out-of-distribution generalization after apparent overfitting, alters training efficiency in deep neural networks, where efficiency is measured as accuracy per unit energy. Using two canonical settings, modular arithmetic and MNIST, we analyze two neural network models under 16-, 32-, and 64-bit precision and use Orthograd to test whether grokking produces noticeable deviations from the typically decreasing dynamics of training efficiency. We consider both short training runs of up to 500 epochs and long training runs of up to 20,000 epochs, and in both cases identify grokking as a sharp improvement in test accuracy after a sustained train-test gap. In the short-horizon experiments, applying Orthograd at progressively stronger levels during early training does not induce grokking, and efficiency remains smoothly decreasing. In the long-horizon experiments, Orthograd induces grokking, but the efficiency curves remain approximately monotonic and show no appreciable local increase at the grokking transition. These results suggest that, in our setting, grokking does not materially alter overall training-efficiency dynamics.
Nov 2, 2026

Dissecting Geometric Constraints in Grokking: Interaction-Dependent Acceleration in Modular Arithmetic

Spherical transformer configurations can accelerate grokking through simultaneous modifications of several model properties. The present study investigated the contributions of these modifications in the published Sphere+Fourier configuration using 960 controlled modular-arithmetic runs. A complete factorial analysis varied residual projection, readout weight normalization, logit scale, and weight decay. Across four matched settings with weight decay, the successful-run mean crossing times without projection were 8-37 times those observed with projection. However, residual projection was insufficient to induce grokking without additional interventions. Various other unprojected configurations also generalized. Since projection altered the magnitude entering the readout, these comparisons could not separate geometry from output scale. A separate 100-run fixed-horizon study demonstrated faster first crossing for the complete configuration across five train/test partitions. Faster crossing did not necessarily correspond to greater persistence over extended training. Control experiments demonstrated rapid grokking without Fourier initialization. Task and depth sweeps also identified conditions in which the configuration failed to reach the criterion by 50K epochs. Accordingly, the observed acceleration depended on interactions among the components and did not extend uniformly across the tested tasks or depths.
Oct 26, 2026

Scaling and Renormalization in Neural Networks: An Effective Renormalization-Group Description of Grokking

Grokking is a delayed transition from memorization to generalization in deep neural networks (NNs). We examine whether scaling and renormalization group (RG) theories can describe this dynamics, establishing a quantitative physical framework for neural generalization transitions. For modular addition on a two-layer NN, an ensemble of trained models defines an order parameter (the squared weight norm) and fluctuation proxies for the heat capacity and the susceptibility, with training epoch and weight decay serving as thermal and field control coordinates. To bridge neural architectures to real-space RG, we construct an exact coupling matrix via a second-order expansion of the loss with respect to per-neuron norms and use its Fiedler vector to define an effective geometry. This spectral ordering yields a monotonic spatial decay of coupling strength that is absent under random permutations. We then execute real-space RG by block-spin aggregating adjacent neurons and parameterizing the coupling matrix into off-diagonal band strengths. Linearizing this local RG map yields relevant scaling exponents and five derived critical exponents, with direct empirical estimates matching RG predictions within 1-10%. Overall, our framework provides a consistent effective description of grokking, suggesting the scaling and renormalization group formalism as a tool to investigate NN dynamics.
Oct 26, 2026

Subspace Crystallization in Grokking: Rank Compression Tracks the Phase Transition

Grokking describes understanding something deeply and intuitively. In neural networks, it is the phenomenon where a network generalizes long after memorizing its training data. This delay has been linked to a fall in the effective rank of the network's weight matrices, but whether this rank compression drives grokking or follows it is still unresolved. We study a mean-field MLP and a one-layer transformer trained on modular arithmetic and observe that: (i) Compression follows the onset, not memorization. Every transformer memorizes its training data within 250 steps, while the grokking onset (the first step at which test accuracy reaches 95%) varies from 6,500 to 21,000 steps. The steepest fall in effective rank comes about 900 steps after the onset, however late the onset occurs, and networks that memorize without grokking compress far less. (ii) Subspace crystallization. We call the span of the fewest top singular directions of a weight matrix that preserve 99% of test accuracy its sufficient subspace. Its size can shrink as the margin between the correct and the best wrong output grows, so we also count the directions needed to keep the outputs within 10%. In the transformer, this count falls during the transition from a quarter or more of the available directions to about a tenth, which we call subspace crystallization. (iii) Imposing low rank does not speed up grokking. Against a factorized full-rank control, capping the rank of the transformer's MLP input weights delays the onset, and capping the rank of its embedding stops 15 of 20 runs from grokking. Compression is therefore a signature of grokking rather than its cause.
Oct 26, 2026

Mapping the Solution-Set Structure of Grokking on Latin Squares

Grokking is a delayed transition from memorisation to generalisation. A network first fits observed examples while remaining near chance on held-out inputs, then generalises abruptly. Prior work has focused mainly on this delay, finding that the network's main loss becomes weight decay after the fitting phase. We name the solution to this optimization problem as the minimum-norm endpoint, and study which tasks make all minimum-norm endpoints generalise from partial observations. Specifically, we model pairwise input tasks as edge colourings of Kq,qK_{q,q}, with Latin colourings as our structured family, and classify each observed instance as all-good, mixed, or no-good by its endpoint set. Furthermore, we prove two contrasting results: (1) Finite-abelian-group families are asymptotically all-good from partial observations; (2) Under a uniform random Latin square, all-good tasks become asymptotically rare for observation-based learners, leaving mixed or no-good behaviour. Moreover, experiments show that relabellings of addition generalise despite their dense polynomial representations. Finally, on tasks of composite order, finite-training results suggest that predictors learn a coarse part of the output before the full label.
Oct 25, 2026

Generalization in Learning: Eyring Formula and Predator-prey Model

In this work, generalization in machine learning is investigated using a predator-prey model. We overview biological and chemical interpretation of the stochastic gradient Langevin dynamics and generative adversarial network. For a particular example of recovering an unknown function by a polynomial of fixed degree from a set of noisy data, the predator-prey model provides better approximation compared to the gradient descent method. Further, thermodynamical arguments, in particular Eyring formula, are used to explain grokking (delayed generalization) phenomenon in machine learning.
Oct 15, 2026

Flat Loss, Evolving Features: Grokking in Modular Addition

Can a network keep learning while its training cross-entropy stays nearly flat at a positive level? We show that it can. On modular addition, a standard testbed for grokking, ReLU networks trained with supported-Polar hidden updates, normalized output-layer updates and weight decay can keep 100% training accuracy while their hidden features change and held-out accuracy rises from zero to above 90%, at relatively flat training cross-entropy. Correct classification need not minimize cross-entropy, which still depends on prediction confidence. We prove this coexistence for one-hidden-layer networks in two finite-window theorems from constructed initializations: one gives a constant gain in the Fourier fraction of the hidden features, and the other holds at arbitrarily low positive loss, where a readout refitted on the training data generalizes before the network. Experiments from random initialization show the same coexistence on a window fixed in advance, and in deeper networks held-out accuracy also rises over post-hoc windows with a net increase in training cross-entropy. With a last-layer rate set per training fraction and head decay scaled with the prime, deeper networks at p=47 and 61 meet a criterion on post-hoc windows, fixed in advance, in nearly all fresh runs. A one-block transformer trained with the same updates and a slowly decaying output gain keeps every training pair correct at every logged checkpoint while its training cross-entropy rises and its held-out accuracy approaches one; with two blocks this holds through the held-out rise, after which training pairs begin to flip. A plateau in training loss need not be a plateau in learning. Code: https://github.com/akashkumar-d/flat-loss-evolving-features.
Oct 13, 2026

Statistical Vignettes on the Grokking Phenomenon

In this work, we study grokking in a simple, analytically tractable setting whose rich phenomenology allows us to disentangle the effects of initialization, signal strength, weight decay, sample size, and input dimension. These factors can produce superficially similar learning curves through distinct mechanisms, complicating their interpretation. Our analysis distinguishes early fitting through nuisance features, core feature learning, and delayed generalization. We identify sharp conditions under which grokking provably occurs and derive analytic asymptotic expressions for the lengths of the generalization plateaus. Our results also characterize regimes of early generalization and failure to reach a prescribed test accuracy target. We show that the interpolation edge constitutes a distinct dynamical regime, where vanishing spectral gaps separate core learning from generalization, helping clarify the role of proximity to interpolation in existing accounts of grokking. The resulting picture is analogous to fast and slow phases in chemical kinetics and suggests that the lazy-to-rich transition discussed in the literature may reflect a similar separation of dynamical time scales. Our theoretical results are faithfully supported by extensive experiments.
Oct 8, 2026

Do Flatter Minima Drive Better Generalization? An Algorithmic Separation in Grokking

Flat loss landscapes have long been linked to better generalization in neural networks. However, its role as a causal mechanism for generalization is less established. Grokking provides an unique testbed to understand this distinction: models are prone to fit observed data using non-generalizing structure and remain in that regime for prolonged periods, transitioning to generalization only under particular training conditions. In this work, we study whether flat loss landscapes can act as a driving mechanism in this transition. While recent work has argued for flatness as a necessary geometric condition for this transition, we find that biasing training toward flatter solutions using sharpness-aware minimization (SAM) is insufficient to reliably induce this transition, despite producing flatter solutions. However, when SAM is paired with mechanisms that drive generalization such as weight decay, an interesting property emerges: SAM can accelerate the transition to generalizing solutions by up to 4x at the epoch-level. We theoretically untangle this relationship between SAM and weight decay using a minimal interpolating two-layer ReLU model with both memorizing and generalizing solutions. We show that even in this simple setup, flatness alone cannot distinguish a memorizing solution from a generalizing one, while weight decay favors generalizing solutions. However, under a local stability analysis, there exists a window where a memorizing interpolant is locally stable under gradient descent but unstable under SAM in the low-norm regime, which can explain SAM's ability to accelerate this transition. Overall, our results provide a more interpretable account of the role of flatness in driving generalization, especially in settings where models are vulnerable to minimizing loss through learning non-generalizing structure.
Sep 30, 2026

Misalignment of Low-Loss Regions Causes Grokking

Grokking refers to the delayed emergence of validation-set generalization after a model has already overfit the training set. Although first observed in small algorithmic tasks trained with transformers, its underlying mechanism remains unsettled. In this work, we develop an analysis framework based on mode connectivity and the geometry of low-loss regions. The framework predicts that the standard modular-arithmetic setting does not always produce grokking: under a symmetry-preserving train/validation split, we observe a stable anti-grokking case in which validation performance does not recover. This counterexample challenges several existing correlational explanations of grokking. More broadly, our analysis framework and results further suggest that grokking arises when the low-loss regions induced by the training and validation partitions are misaligned. Once these regions become well aligned, training hyperparameters alone cannot produce grokking and the observed dynamics collapse to either trainable or non-trainable behavior.
Sep 29, 2026

Grokking through the Lens of Minimum-Norm Interpolation

Grokking shows that fitting the training data and learning the underlying signal can occur at very different stages. However, existing theories offer limited quantitative insight into how this delayed generalization depends on inductive bias and signal structure. Our work addresses the gap by developing a statistical theory that characterizes how regularization geometry and signal sparsity govern generalization near interpolation. In particular, we focus on the prototypical setting of high-dimensional regression and identify regimes in which sparsity-promoting regularization makes exact interpolation much more accurate than approximate fitting. In strongly overparameterized noiseless problems, we prove a zero--one generalization law and construct a family of convex norms whose interpolators transition from the trivial risk of the all-zero predictor to exact recovery, while keeping the training error equal to 00. Furthermore, when feature dimension and sample size are proportional, we provide a precise characterization of training and generalization errors along ℓr\ell_r-regularization paths. This in turn allows us to quantify the generalization gain that remains near interpolation: we show that this gain increases as the norm becomes more sparsity-promoting and as the target becomes sparser, with a sharp drop in generalization reached for noiseless data and ℓ1\ell_1 regularization. Experiments on diagonal linear networks and transformers trained on modular arithmetic demonstrate the generality of our theoretical predictions. Finally, beyond grokking, our work reveals a statistical instability in minimum-norm interpolation: small perturbations in the regularization strength can lead to drastically different generalization, while preserving small training error.
Sep 22, 2026

A Spectral Theory of Grokking: Weight Decay induces Feature Learning

In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fixed neural tangent kernel (NTK) regime to one in which task-relevant kernel eigendirections continue to evolve. We provide a quantitative theory for how this transition from lazy to rich learning can produce delayed generalization. For homogeneous networks trained with squared loss and L2L_2 weight decay, we show that a finite residual remains after memorization, with larger residual fractions in target components associated with smaller NTK eigenvalues. These residuals feed back into the dynamics of the NTK itself, and projecting the resulting dynamics onto task-relevant spectral directions yields a reduced system in which residual-driven kernel growth competes with weight decay. This system predicts that the grokking timescale is controlled by the product of learning rate and weight decay, that feature learning slows logarithmically near a critical decay above which task-aligned NTK structure can no longer support generalization, and that stronger decay can prevent fitting altogether. We test these predictions in modular addition. In a homogeneous MLP, task-aligned Fourier structure continues to emerge in the NTK after training accuracy has saturated, and an 84×\times90-grid of trained networks across varying learning rate and weight decay recovers the predicted phase geometry and inverse-product scaling of the generalization time with learning rate and weight decay. A one-block Transformer shows similar macroscopic phase structure in a 42×\times45-grid, as well as the same transition-time scaling despite violating exact homogeneity. Together, these results provide a mechanistic derivation connecting post-fit feature learning to both the onset of generalization and its phase structure in the learning rate and weight decay plane.
Sep 22, 2026

An Exploratory Replica-Overlap Probe of the Grokking Transition

We trained 64 independently seeded networks in four configurations, continuing each to sustained convergence or a 40,000-epoch ceiling. We then asked whether an RSB-inspired distribution of pairwise weight overlaps changes across the grokking transition. It is the alignment step, not the overlap statistic, that determines what this registered probe can report. The registered implementation permutes hidden units without the corresponding bias and head-internal permutations and therefore does not preserve the network function. Every q_wt value computed through this alignment inherits the defect; q_fn does not, because it is computed from predictions of the unpermuted models. The numerical-precision requirement also failed, and an audit found protocol deviations. Consequently, the pre-registered rule gives no verdict: registered outcome UNDETERMINED (reason code C0_INSTRUMENT_INVALID). These data provide neither a confirmatory null nor a validated reading of the Parisi order parameter. Only frac40 cleared the 12/16 checkpoint-completeness requirement. For this configuration, a post-hoc criterion applied to the same data gave a Hartigan-dip interval containing zero (95% CI for Delta dip = [-0.017, 0.034]), whereas the overlap standard deviation increased by a factor of about 5.6. A post-hoc calibration assigns the dip test zero power at the simulated separations; the interval is therefore uninformative, not evidence of no change. The standard-deviation ratio is the only statistic here with power at the observed effect. Ensemble loss was near-flat only under the pre-specified 1% threshold. Finally, grokking rates of 0/16, 11/16 and 16/16 remain descriptive because train fraction is confounded with split identity.
Sep 16, 2026

Beyond Embedding Transfer: Architectural Interfaces, Iso-Parameter Scaling, and Preconditioner-Governed Consolidation in Grokking

Grokking, or delayed generalization after memorization, incurs substantial training steps across algebraic tasks. Cross-operator transfer from a grokked donor accelerates target acquisition, yet post-grokking AdamW continuation triggers test-accuracy relapse as unannealed updates drift across residual interfaces and decaying second moments amplify late gradients. Across depths one to three on modular arithmetic (Z113\mathbb{Z}_{113}), non-Abelian S5S_5 conjugation, and real-sensory MNIST modular arithmetic, we separate representational transfer from preconditioner-governed consolidation across thirteen experimental batteries. First, co-transferring internal blocks accelerates one-layer and two-layer modular takeoff beyond boundary interfaces, while graded prefix pinning bounds depth-three drift under unannealed continuation. Second, an iso-parameter S5S_5 scaling grid separates attention head dimension from MLP width: widening two-head attention to dimension 6464 reaches 98.54%98.54\% cold accuracy at 427k427\mathrm{k} parameters and 85.95%85.95\% boundary-only transfer, while final-slot representations refine conjugation directly across blocks without an intermediate binary-product bottleneck. Third, Plateau-Gated Leaky Consolidation pairs validation-envelope step damping with leaky second-moment decay, reaching 84.85%84.85\% zero-leakage validation-gated risk-constrained accuracy across five pre-saturation two-layer S5S_5 suites while cutting step budget relative to hard anchoring. Fourth, transferring a grokked visual trunk and blocks to image-disjoint MNIST targets reaches 92.27%92.27\% and 90.76%90.76\% accuracy, prunes odd centroid harmonics, and reaches 90.42%90.42\% risk-constrained accuracy across 60/6060/60 branches without hyperparameter retuning.
Sep 14, 2026

Structured Features Overfit Where Random Features Grok

Xu, Vardi and Safran (ICML 2026) prove that over-parameterized ridge regression over an unstructured random Gaussian feature map groks, with the delay between memorization and generalization growing as 1/λ1/λ in the weight decay. We show that on a structured feature map the same delay does not appear. For a band-limited Fourier feature map over Zp2\mathbb{Z}_p^2 carrying a single-character target that lies inside the expressible class, enlarging the band at fixed positive weight decay drives peak held-out accuracy monotonically from 1.001.00 to 0.070.07, with no memorize-then-generalize regime anywhere along the sweep. The degradation is not an interpolation effect. It sets in at capacity ratio q/n=0.638q/n = 0.638, far below the interpolation threshold, on separate grounds from the exact null space that appears above it. What does have a sharp boundary is the active support. Holding the nominal dimension fixed and masking the band back to 10891089 active modes restores held-out accuracy of 1.0001.000 with zero variance across seeds, while the full 42254225-mode band collapses to 0.1850.185. The number of active modes acts through the teacher-weighted spectrum of the empirical Gram matrix and not through the capacity ratio, which makes this a statement about feature geometry and not a restatement of double descent.
Sep 9, 2026

Quantifying the Memorization-to-Generalization Transition: Scaling Laws and Phase Structure in Grokking

Neural networks trained past memorization frequently undergo a delayed transition to generalization, a phenomenon known as grokking. Despite theoretical progress on why this transition occurs, the quantitative structure of when it occurs in hyperparameter space remains uncharacterized. We map the memorization-to-generalization boundary across 384 configurations of two-hidden-layer MLPs on modular arithmetic, fitting a power-law scaling relation for generalization onset time: Tgrok∝H−0.27 D−2.04 η−0.50 λ−0.64T_{\mathrm{grok}} \propto H^{-0.27}\, D^{-2.04}\, η^{-0.50}\, λ^{-0.64} (R2=0.732R^2 = 0.732; 0.8210.821 with interactions). The exponent hierarchy reveals that data complexity (D−2.04D^{-2.04}) is the dominant driver of regime transition, not model capacity (H−0.27H^{-0.27}): doubling data accelerates generalization by ∼4×{\sim}4\times, while doubling width yields only ∼1.2×{\sim}1.2\times. A sharp phase boundary at weight decay λ≳1.0λ\gtrsim 1.0 separates grokking from non-grokking configurations, and weight norm trajectories show monotonic compression during the transition, consistent with implicit regularization selecting low-complexity solutions. These results provide a quantitative foundation for predicting and controlling regime transitions in overparameterized networks.
Aug 28, 2026

Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons

Grokking is a delayed transition from memorization to generalization that is often accompanied by substantial reorganization of internal representations. This paper studies whether biologically inspired mechanisms, many of which are not commonly incorporated into artificial neural networks, can actively promote this transition by regulating hidden-layer computation at the levels of neuronal activity, response, and effective connectivity. We augment a multilayer perceptron with input gating, structural plasticity, gain modulation, threshold modulation, homeostasis, lateral inhibition, and activation decorrelation, and evaluate these mechanisms through systematic ablations on two established grokking benchmarks: sparse parity and noisy XOR classification. The results show that the mechanisms contribute unequally to generalization. Homeostasis provides the strongest and most consistent benefit, while structural sparsification emerges as the second major mechanism. The remaining biologically inspired mechanisms have smaller or less consistent effects in the present experiments. For both problems, the results support the common principle that explicit regulation of neuron utilization and effective connectivity can improve the emergence of generalizable internal computation. These findings motivate broader investigation of biologically inspired activity regulation and adaptive sparsification, including in large language models, where they may accelerate the development of generalizable representations and reduce the optimization time required for robust generalization.
Aug 26, 2026

Mapping the Emergence of Regularization-Driven Dynamics in Grokking

For overparameterized neural networks, many solutions can fit the training data equally well while behaving very differently on unseen samples. Grokking separates training fit from visible generalization, providing a window for studying how this selection develops during training. We sweep short, fixed-duration weight decay (WD) perturbations across the pre-generalization plateau and measure how they shift later generalization time. Across three grokking tasks, these shifts are unordered early in the plateau but later form a stable dose ordering before visible generalization, with stronger WD increases leading to earlier generalization and stronger WD decreases leading to later generalization. Test-loss barriers between perturbed and baseline generalization checkpoints collapse toward zero while the ordered timing effects persist. A similar response reorganization is observed under ℓ1\ell_1 regularization in the grokking setting of Junior et al. (2025). Drawing on Waddington's developmental landscape as an analogy, we call this combination of increasingly constrained solution selection and persistent dose-ordered timing shifts the canalization of grokking solution selection. Together, our response maps and loss-barrier measurements reveal a dynamical reorganization before visible generalization that is consistent with the theoretical picture of regularization-driven motion along a stable slow manifold (Boursier et al., 2025).
Aug 14, 2026

Is Grokking a Loss of Normal Hyperbolicity of the Interpolation Manifold?

A recent line of work recasts the post-memorization phase of grokking as constrained optimization: once a network interpolates the training set, weight decay drives a slow drift along the zero-loss manifold toward lower norm. In the language of dynamical systems, this is a fast-slow system in which the interpolation manifold plays the role of a slow manifold. We ask a question that this framing makes natural but the existing literature does not address: is the sharp generalization transition a loss of normal hyperbolicity of that manifold: a fold- or bifurcation-like event in which a normal restoring direction goes flat? Or does the manifold stay uniformly attracting while generalization happens by smooth drift? We propose a simple, optimizer-agnostic diagnostic: the smallest nonzero singular value σmin⁡+(J)σ_{\min}^{+}(\mathbf J) of the residual Jacobian, which, for the squared loss, equals the slowest normal restoring rate of the manifold. On a two-layer ReLU network trained to grok modular addition under squared loss, σmin⁡+(J)σ_{\min}^{+}(\mathbf J) does not collapse at the transition; it is near zero only before memorization and attains its largest values during the transition. The result holds across five seeds, and the six smallest singular values behave identically; there is no subspace-local collapse either. This is preliminary evidence against the bifurcation hypothesis and in favor of the smooth-contraction picture. We are explicit that a single-setting, gradual-transition experiment under Adam optimizer does not prove the absence of a bifurcation; it constrains where one could hide.
Aug 14, 2026

Algorithmic Information Dynamics of Learning: A Certified, Differentiable Complexity Controller for Grokking

Algorithmic Information Dynamics (AID) studies systems by perturbing them and measuring changes in algorithmic complexity, but its usual estimator, the Block Decomposition Method, is piecewise constant, restricting the calculus to finite differences. We use KsFCDMK^{\mathrm{CDM}}_{\mathrm{s}F}, a certified, differentiable estimator, to bring the calculus into learning dynamics: grokking, where a complexity order parameter is known but has not been made to act. As a transient loss kick, the estimator becomes a controller that accelerates grokking in Levin's description-length--versus-time sense, within a data-dependent Occam boundary whose finite-size trend, fc∼ln⁡p/pf_c\sim\ln p/p, is consistent with a coupon-collector interpretation. Ablations show that a complexity gate matches a train-loss gate in rescuing failing seeds with 27%27\% less intervention; among the tested signals, only map complexity marks the transition's completion; the certified prior and the per-parameter ∇K\nabla K attribution are both fungible (a uniform-prior sensor makes bit-identical gate decisions, and random supports match ∇K\nabla K-selected ones above a sparsity threshold); and direct field perturbation shows a nucleation-like response to the Occam field (no linear regime is resolved over the probed amplitudes, so these measurements do not justify a fluctuation--dissipation surrogate), with a finite-field response growing by orders of magnitude toward the phase-transition. These measurements account for the empirically tuned staircase: bang--bang pulses, stall-fired and released on yield, whose iteration plausibly builds the response it exploits. The kick transfers to sparse parity and to a transformer; a sustained weight-space loss fails. The algorithmic estimator's distinct contribution is timing (when to fire and when to release), not attribution.
Aug 7, 2026

Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers

Muon-trained modular-arithmetic transformers can lose accuracy while retaining linearly decodable task information. Adjacent swaps localize five captured unnormalized failures to AdamW readout updates. Multiplying the actual readout displacement by the large feature mean produces a class-dependent logit offset shared across inputs that nearly reproduces each failure. Training-only decoders recover 98.20-100% held-out accuracy. Correcting cross-entropy derivative errors stabilizes five matched branches through step 100,000; four prospective accurate-CE RMS runs fail through embedding updates.
Aug 3, 2026

Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swapping

Grokking is a striking phenomenon in neural network training, where a model can undergo a prolonged period of pure memorization before abrupt generalization. While previous works have attempted to interpret it through classical machine learning mechanisms like weight norm, recent research draws an analogy from statistical physics, framing grokking as a form of computational glass relaxation. This theory defines the initial memorization as a result of fast cooling' where the training loss is reduced so quickly that a glass state is formed, followed by a slow relaxation' towards final generalization. Although providing a unifying framework for representative grokking theories, this perspective has remained largely at the theoretical on macroscopic level without direct empirical validation on training dynamics. Here we introduce a three-component framework to directly characterize the training dynamics via parameter mobility (PM), and two representative measurements from glassy dynamics: replica correlation (RC) and fractal dimension (FD). We demonstrate that standard optimization presents clear signatures of glass dynamics and inherently traps the grokking network in a kinetic arrested memorization state with a collapsed mobility, strong history dependence, and channel-like motions. This quantitative agreement motivates us to introduce State-Aware Monte Carlo Parameter Swapping (SAM-Swap), an optimization plug-in that can accelerate generalization, inspired by swap Monte Carlo algorithm widely used in glass dynamics. Comparing SAM-Swap, weight decay, and Gaussian gradient noise, we find that accelerated generalization is consistently associated with random exploration in the parameter space, similar to diffusion in physics.
Jul 27, 2026

Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries

Delayed generalization, or grokking, remains poorly understood despite extensive empirical study. We identify an exactly solvable late-time relaxation mechanism for grokking in linear models trained with full-batch heavy-ball optimization and weight decay, together with a locally quadratic extension to nonlinear neural networks. Our analysis reveals a distinguished population-active component of the empirical null space, which we call the grokking subspace. Along this subspace, the training predictions remain unchanged, leaving weight decay as the sole restoring force and giving rise to a slow dissipative relaxation governed by an exact discrete-time and continuous-time law. We show that only this subspace contributes to the slow asymptotic decay of the population risk and derive explicit iteration-scale predictions for the grokking time, recovering the familiar (1−β)/(ηλ)(1-β)/(ηλ) scaling in the weak-regularization regime. The theory further predicts distinct effects of optimizer choice, distinguishing coupled L2L_2 regularization from decoupled weight decay, and yields causal predictions for interventions that modify the grokking component. We verify all theoretical identities without fitted parameters in a synthetic model where every subspace and relaxation rate is computable in closed form. We further observe genuine delayed generalization in modular addition, where the measured delay follows the predicted scaling and the late-time relaxation agrees closely with the theoretical clock.
Jul 21, 2026

Tensor Network Machine Learning for Wildfire Susceptibility Mapping: from Grokking Dynamics to Quantum Mixedness of Class Representations

A quantum-inspired tensor network framework for wildfire susceptibility classification in the Gargano region is introduced, leveraging AlphaEarth embeddings and Matrix Product State models. The approach combines scalable geospatial representations with an interpretable quantum mask, enabling both binary and multiclass classification of wildfire susceptibility. Beyond predictive performance, the study reveals a pronounced grokking transition in the binary case and provides a detailed analysis of inter-class confusion in the multiclass setting. By introducing level-resolved mixedness diagnostics based on reduced density matrices, we show that the MPS classifier naturally encodes a hierarchy of class distinguishability, with non-adjacent categories becoming more separable than neighboring ones. These results demonstrate that tensor network models not only achieve competitive classification accuracy but also offer a physically grounded framework to quantify and interpret class separability in complex environmental datasets.
Jul 15, 2026

Algebraic Representability as the Limiting Regime of Grokking: An Exactly Solvable Model with Holomorphic Activations

Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capacity: too little and the network memorises slowly or not at all, too much and it generalises almost immediately. What happens at the extreme of this spectrum, when the architecture's expressible function class collapses to a finite-dimensional algebraic variety? We study two-layer networks with a holomorphic monomial activation sigma(z)=z^k, trained on modular tasks encoded via roots of unity. Here the network output, regardless of hidden width, is confined to a (k+1)-dimensional subspace of characters of (Z_p)^2, an O(k/p^2) slice of the full function space. We give a complete algebraic characterisation of this subspace: a task is representable if and only if its discrete Fourier support lies on the diagonal u+v = k (mod p), which for linear-phase targets reduces to the arithmetic criterion m+n=k. This is not merely a constraint on eventual generalisation but on memorisation itself: because the outputs are algebraically confined, a non-representable target cannot be fit even on the training set, and we prove a positive lower bound on the training loss, independent of width. Across 585 runs the algebraic prediction matches the observed outcome with 99.8% accuracy, with no memorisation regime and no grokking; outcomes split cleanly into instant success and outright failure. This binary behaviour is the limiting case of the capacity-grokking relationship: when the expressible class shrinks to a fixed algebraic object, the question of when a network will grok dissolves into whether it can represent the target at all. A bottleneck ablation connects this extreme to standard networks, tracing a continuous path from representational failure, through memorisation without generalisation, to grokking with a shrinking gap as capacity grows.
Jul 14, 2026

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

Companion work showed the grokking delay is causally the time to form task-structured representations, injectable via a contrastive prior. Here we characterize what makes such a prior work, across four axes, in 188 new runs. Content: a coherent, learnable prior built from the wrong feature family (magnitude bands) blocks generalization like a random partition (1/15 vs 0/20 grok; p=0.43p=0.43 between them), confirming the companion's prediction that priors act at the level of the circuit's features. Supervision: a fully label-free invariance prior -- positives are commuted pairs (a,b)∼(b,a)(a,b)\sim(b,a) only -- generalizes in 15/15 runs at a median 2.7×2.7\times speedup, more reliably than the label-supervised prior itself (p=0.038p=0.038), and combined with a weight-norm clamp yields the strongest method we test (median 17×17\times, 5/5) -- strongest meaning reliably fast: plain cross-entropy with a clamp matches this speed only at the exact critical norm, while the prior keeps it fast across the entire clamp range. Timing: the prior is only needed early -- applied solely during the first 2000 epochs (4% of budget) it generalizes 10/10 at 2.7×2.7\times, beating continuous application (8/10, 1.25×1.25\times) and a duration-matched later window (2.1×2.1\times). Setting: the dissociation replicates on modular multiplication and across depths and normalization variants, and a clamp sweep quantifies the companion's central claim: structure injection flattens the weight-norm delay-law exponent about 17-fold (plain cross-entropy slows 31×31\times per +10 norm units, a lower bound as higher cells are censored, versus 1.22×1.22\times with the prior). Honest boundary: tasks that generalize before memorizing have no delay to control. Feature-family alignment decides whether a prior permits generalization; invariance content suffices for acceleration without labels; a brief early window captures nearly all of the benefit.
Jul 13, 2026

How to Tame Grokking: Representation Geometry as a Control Signal

Grokking is a phenomenon in which neural networks initially memorize training data and only later exhibit strong generalization after prolonged optimization. Despite extensive recent study, the factors influencing the emergence and timing of grokking remain incompletely understood. We investigate the relationship between representation geometry and delayed generalization. We find that dimensionality collapse consistently precedes the onset of grokking in all evaluated settings. Motivated by these observations, we introduce Geometric Dimensionality Regularization (GeomDR), a simple spectral regularizer that modifies the effective dimensionality of hidden representations during training. Across modular addition, modular division, and permutation composition tasks, GeomDR consistently alters grokking dynamics and can substantially accelerate the onset of generalization depending on the intervention schedule and target dimensionality. In several settings, grokking is accelerated by up to 52 times relative to standard AdamW training. Similar qualitative effects are observed in both multilayer perceptrons and transformers. Together, these results suggest that representation geometry can serve as an effective control signal for grokking and provide evidence that geometric interventions offer a practical approach for studying and influencing delayed generalization in neural networks.
Jul 7, 2026

At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics

On modular arithmetic, a network's embedding keeps compressing for tens of thousands of steps after it has already generalized. Reading effective rank at the grokking transition overstates the converged value by 3-5x on an MLP, and by 1.3-1.5x on a transformer trained to convergence; on the MLP it also erases which cells compress at all. Compression lags the accuracy transition by an amount on the order of the time-to-grok, at least 10,000 steps, rather than coinciding with it. A one-variable ablation shows what sets the lag size: adding LayerNorm to an otherwise identical transformer moves the fraction of compression done by the grok step from 0.87 to 0.25, and a pre-registered control rules out scale invariance as the mechanism. We package this as an audit that separates onset from compression, flags censoring, excludes boundary cells that never fully generalize, and checks that the reference floor has plateaued, with an adversarial suite that caught a false-confidence bug in our own branch. A secondary, MLP-specific depth law linking norm budget to converged floor fails a generality test on a transformer and flips sign under free weight decay. Code and the toolkit are released.
Jul 7, 2026

Cross-Trajectory Chimera Interventions Reveal Dissociable Roles of Weight Magnitude and Direction in Grokking

Which properties of a partially trained network are causally portable to a different, independently trained network? Single-trajectory interventions show necessity within one run, not portability across runs. We introduce cross-trajectory chimera interventions: given two runs from different seeds, we split each weight vector into a norm and a unit direction, recombine one run's norm with the other's direction, and continue training. On two modular-arithmetic tasks that grok, the components dissociate. Direction carries a transferable, donor-specific circuit identity: implanting a donor's direction at the recipient's norm drives the run to the donor's circuit in 40/40 cases, while an angle-matched random control yields no shift. The transfer is threshold-like, and its location is predicted by the recipient's norm, separating perfectly by norm class over all 20 pairs (joint permutation probability 1.9e-4). Norm carries only a modest, distributed delay effect and no identity signal. An adaptive bisection procedure localizes the threshold to +/-1/64. Direction indexes which solution a trajectory approaches; norm governs how susceptible that identity is to being overwritten.
Jul 6, 2026

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

Grokking -- the delayed onset of generalization long after a network has fit its training set - -is usually studied in models too large to read completely and reported from single training runs. We instead study a publicly released ~11,856-parameter Llama-style transformer (Glimmer-1-Base) on modular arithmetic, small enough to enumerate its weights, attention, and full input-output map, and we measure grokking as a multi-seed rate rather than a single outcome. In this fully-tractable regime grokking is a conditional, fragile phase transition. It is gated by training-set coverage, whose threshold tracks output cardinality (the modulus) more than task structure, an ordering that holds above the transition and across a ten-fold change in domain size. Weight decay reproduces the Omnigrok inverted-U at 12K parameters, a positive control on the rate measurement. Grokking also sits on a numerical knife-edge: two perturbations of the floating-point environment -- CPU thread count (reduction order) and CPU-versus-GPU execution -- each flip a minority of same-seed outcomes without a detectable shift in the aggregate rate. Decomposition into sub-task specialists helps chiefly by making coverage cheap rather than by adding supervision. Methodologically, multi-seed control under a fixed numerical environment overturns three dramatic single-run narratives in our own data, each a seed confound. The unit of evidence for grokking must therefore be a multi-seed rate under a pinned numerical environment, checked where possible against a direct reading of the model.