Overview

Logistic regression predicts binary or multiclass outcomes by mapping input features to probabilities, making its coefficients relatively interpretable and the method useful in fields such as medicine, credit, and text classification. Research studies how to fit these models with gradient descent and stochastic or federated optimization, regularization such as L1, and extensions for missing, noisy, private, or externally supplied data. Theory examines finite-sample estimation and training dynamics, including step-size effects, oscillations, max-margin behavior on separable data, and class imbalance; applications also focus on calibration, fairness, and label noise. A central tension is that simple models can be easier to interpret and deploy but may miss nonlinear patterns, while reliable performance with imperfect data and practical solver choices remains challenging.

Latest papers

41 papers4 papers in the last four weeks, down 43% on the four weeks before. 0.0% of all new papers.

Mar 22, 2026

Amortized Variational Inference for Logistic Regression with Missing Covariates

Missing covariate data pose a significant challenge to statistical inference and machine learning, particularly for classification tasks like logistic regression. Classical iterative approaches (EM, multiple imputation) are often computationally intensive, sensitive to high missingness rates, and limited in uncertainty propagation. Recent deep generative models based on VAEs show promise but rely on complex latent representations. We propose Amortized Variational Inference for Logistic Regression (AV-LR), a unified end-to-end framework for binary logistic regression with missing covariates. AV-LR integrates a probabilistic generative model with a simple amortized inference network, trained jointly by maximizing the evidence lower bound. Unlike competing methods, AV-LR performs inference directly in the space of missing data without additional latent variables, using a single inference network and a linear layer that jointly estimate regression parameters and the missingness mechanism. AV-LR achieves estimation accuracy comparable to or better than state-of-the-art EM-like algorithms, with significantly lower computational cost. It naturally extends to missing-not-at-random settings by explicitly modeling the missingness mechanism. Empirical results on synthetic and real-world datasets confirm its effectiveness and efficiency across various missing-data scenarios.
Mar 21, 2026

Hard labels sampled from sparse targets mislead rotation invariant algorithms

One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logistic link function to a linear score. In binary logistic regression, the feedback can be either soft labels, corresponding to the true conditional probability of the data (as in distillation), or sampled hard labels (taking values ±1\pm 1). We point out a fundamental problem that arises even in a particularly favorable setting, where the goal is to learn a noise-free soft target of the form σ(x⊤w⋆)σ(\mathbf{x}^{\top}\mathbf{w}^{\star}). In the over-constrained case (i.e. the number of samples nn exceeds the input dimension dd) with examples (xi,σ(xi⊤w⋆))(\mathbf{x}_i,σ(\mathbf{x}_i^{\top}\mathbf{w}^{\star})), it is sufficient to recover w⋆\mathbf{w}^{\star} and hence achieve the Bayes risk. However, we prove that when the examples are labeled by hard labels yiy_i sampled from the same conditional distribution σ(xi⊤w⋆)σ(\mathbf{x}_i^{\top}\mathbf{w}^{\star}) and w⋆\mathbf{w}^{\star} is ss-sparse, then rotation-invariant algorithms are provably suboptimal: they incur an excess risk Ω ⁣(d−1n)Ω\!\left(\frac{d-1}{n}\right), while there are simple non-rotation invariant algorithms with excess risk O(slog⁡dn)O(\frac{s\log d}{n}). The simplest rotation invariant algorithm is gradient descent on the logistic loss (with early stopping). A simple non-rotation-invariant algorithm for sparse targets that achieves the above upper bounds uses gradient descent on the weights ui,viu_i,v_i, where now the linear weight wiw_i is reparameterized as uiviu_iv_i.
Feb 23, 2026

Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health

Background: Childhood and adolescent overweight and obesity remain major public health concerns in the United States and are shaped by behavioral, household, and community factors. Their joint predictive structure at the population level remains incompletely characterized. Objectives: The study aims to identify multilevel predictors of overweight and obesity among U.S. adolescents and compare the predictive performance, calibration, and subgroup equity of statistical, machine-learning, and deep-learning models. Data and Methods: We analyze 18,792 children aged 10-17 years from the 2021 National Survey of Children's Health. Overweight/obesity is defined using BMI categories. Predictors included diet, physical activity, sleep, parental stress, socioeconomic conditions, adverse experiences, and neighborhood characteristics. Models include logistic regression, random forest, gradient boosting, XGBoost, LightGBM, multilayer perceptron, and TabNet. Performance is evaluated using AUC, accuracy, precision, recall, F1 score, and Brier score. Results: Discrimination range from 0.66 to 0.79. Logistic regression, gradient boosting, and MLP showed the most stable balance of discrimination and calibration. Boosting and deep learning modestly improve recall and F1 score. No model was uniformly superior. Performance disparities across race and poverty groups persist across algorithms. Conclusion: Increased model complexity yields limited gains over logistic regression. Predictors consistently span behavioral, household, and neighborhood domains. Persistent subgroup disparities indicate the need for improved data quality and equity-focused surveillance rather than greater algorithmic complexity.
Feb 21, 2026

Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of stability, where optimization trajectories become unstable and difficult to analyze. Existing results for separable logistic regression achieve faster convergence by explicitly leveraging such unstable regimes through constant or adaptive large step sizes. In this paper, we show that instability is not inherent to acceleration. We prove that gradient descent with a simple, non-adaptive increasing step-size schedule achieves exponential convergence for separable logistic regression under a margin condition, while remaining entirely within a stable optimization regime. The resulting method is anytime and does not require prior knowledge of the optimization horizon or target accuracy. We also establish exponential convergence of stochastic gradient descent using a lightweight adaptive step-size rule that avoids line search and specialized procedures, improving upon existing polynomial-rate guarantees. Together, our results demonstrate that carefully structured step-size growth alone suffices to obtain exponential acceleration for both gradient descent and stochastic gradient descent.
Oct 22, 2025

RLIE: Rule Generation with Logistic Regression, Iterative Refinement, and Evaluation for Large Language Models

Large Language Models (LLMs) can propose rules in natural language, sidestepping the need for a predefined predicate space in traditional rule learning. Yet many LLM-based approaches ignore interactions among rules, and the opportunity to couple LLMs with probabilistic rule learning for robust inference remains underexplored. We present RLIE, a unified framework that integrates LLMs with probabilistic modeling to learn a set of weighted rules. RLIE has four stages: (1) Rule generation, where an LLM proposes and filters candidates; (2) Logistic regression, which learns probabilistic weights for global selection and calibration; (3) Iterative refinement, which updates the rule set using prediction errors; and (4) Evaluation, which compares the weighted rule set as a direct classifier with methods that inject rules into an LLM. We evaluate multiple inference strategies on real-world datasets. Applying rules directly with their learned weights yields superior performance, whereas prompting LLMs with the rules, weights, and logistic-model outputs surprisingly degrades accuracy. This supports the view that LLMs excel at semantic generation and interpretation but are less reliable for precise probabilistic integration. RLIE clarifies the potential and limitations of LLMs for inductive reasoning and couples them with classic probabilistic rule combination methods to enable more reliable neuro-symbolic reasoning.
Oct 15, 2025

Exact Dynamics of Multi-class Stochastic Gradient Descent

We develop a framework for analyzing the learning dynamics of high-dimensional problems trained using one-pass stochastic gradient descent (SGD) with data from multiple anisotropic classes. Our main theorem provides exact expressions for quantities of interest, including the risk and the overlap with the true signal, in terms of a deterministic system of ODEs, valid in the high-dimensional limit. The theorem holds for a broad class of optimization problems and extends to settings where the number of classes grows with dimension. To illustrate its utility, we investigate in detail the effect of the data's anisotropic structure on the problems of binary logistic regression and least-squares (LS) loss. We study the LS in a linear multiclass setup and derive a learning-rate threshold that depends on the average eigenvalue of the covariance matrices. In the binary logistic regression, we study three cases: isotropic covariances, data covariance matrices with a large fraction of zero eigenvalues (denoted as the zero-one model), and covariance matrices with power-law spectra. We show that a structural phase transition occurs. In particular, for the zero-one model and the power-law model with sufficiently large power, SGD aligns more closely with values of the class mean that are projected onto the ``clean directions'' (i.e., directions of smaller variance). This is supported by analytical studies and numerical simulations, which show the exact asymptotic behavior of the loss in the high-dimensional limit. The effects of data anisotropy that we demonstrate are likely to hold beyond these examples and illustrate one application of the broader theorem that we prove.
Jul 15, 2025

Gradient Descent on Logistic Regression: Do Large Step-Sizes Work with Data on the Sphere?

Gradient descent on logistic regression has many fascinating properties not fully captured by classical analyses. For linearly separable data, the iterates converge in direction to the maximum-margin separator regardless of how large the step size is. For non-separable data, however, cycles may occur even for step sizes below the local stability threshold of 2/λ∗2/λ^*, where λ∗λ^* is the largest eigenvalue of the Hessian at the solution. We ask whether requiring all examples to have equal norm is a sufficient condition for global convergence below this threshold. We prove that this is indeed true in one dimension. In higher dimensions, even equal-norm datasets can produce cycles, although global convergence holds for the population loss when the examples are uniformly distributed on the sphere. Finally, in one dimension, we relax the equal-norm assumption to an annulus condition that ensures global convergence below the stability threshold, suggesting a path towards analogous sufficient conditions in higher dimensions.
Mar 7, 2025

Near-Polynomially Competitive Active Logistic Regression

We address the problem of active logistic regression in the realizable setting. It is well known that active learning can require exponentially fewer label queries compared to passive learning, in some cases using log⁡1\eps\log \frac{1}{\eps} rather than \poly(1/\eps)\poly(1/\eps) labels to get error \eps\eps larger than the optimum. We present the first algorithm that is polynomially competitive with the optimal algorithm on every input instance, up to a factor d2d^2 and factors polylogarithmic in the error and domain size. In particular, on a simple family of logistic threshold instances with a uniform distribution, our algorithm uses \polylog(1/\eps)\polylog(1/\eps) labels, whereas every passive learner requires Ω(1/\eps2)Ω(1/\eps^2) labels. Our algorithm is based on sampling and can be extended to learn more general class of functions. We further support our theoretical results with experiments demonstrating performance gains for logistic regression compared to existing active learning algorithms.
Dec 27, 2024

Stroke Prediction using Clinical and Social Features in Machine Learning

Every year in the United States, 800,000 individuals suffer a stroke - one person every 40 seconds, with a death occurring every four minutes. While individual factors vary, certain predictors are more prevalent in determining stroke risk. As strokes are the second leading cause of death and disability worldwide, predicting stroke likelihood based on lifestyle factors is crucial. Showing individuals their stroke risk could motivate lifestyle changes, and machine learning offers solutions to this prediction challenge. Neural networks excel at predicting outcomes based on training features like lifestyle factors, however, they're not the only option. Logistic regression models can also effectively compute the likelihood of binary outcomes based on independent variables, making them well-suited for stroke prediction. This analysis will compare both neural networks (dense and convolutional) and logistic regression models for stroke prediction, examining their pros, cons, and differences to develop the most effective predictor that minimizes false negatives.
Jun 7, 2024

Gradient Descent on Logistic Regression with Non-Separable Data and Large Step Sizes

We study gradient descent (GD) dynamics on logistic regression problems with large, constant step sizes. For linearly-separable data, it is known that GD converges to the minimizer with arbitrarily large step sizes, a property which no longer holds when the problem is not separable. In fact, the behaviour can be much more complex -- a sequence of period-doubling bifurcations begins at the critical step size 2/λ2/λ, where λλ is the largest eigenvalue of the Hessian at the solution. Using a smaller-than-critical step size guarantees convergence if initialized nearby the solution: but does this suffice globally? In one dimension, we show that a step size less than 1/λ1/λ suffices for global convergence. However, for all step sizes between 1/λ1/λ and the critical step size 2/λ2/λ, one can construct a dataset such that GD converges to a stable cycle. In higher dimensions, this is actually possible even for step sizes less than 1/λ1/λ. Our results show that although local convergence is guaranteed for all step sizes less than the critical step size, global convergence is not, and GD may instead converge to a cycle depending on the initialization.
Jan 26, 2022

Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant

Training logistic regression over encrypted data has emerged as a prominent approach to addressing security concerns in recent years. In this paper, we introduce an efficient gradient variant, termed the quadratic gradient, which is specifically designed for privacy-preserving logistic regression while remaining equally effective in plaintext optimization. By incorporating this quadratic gradient, we enhance Nesterov's Accelerated Gradient (NAG), Adaptive Gradient (AdaGrad), and Adam algorithms. We evaluate these enhanced algorithms across various datasets, with experimental results demonstrating state-of-the-art convergence rates that significantly outperform traditional first-order gradient methods. Furthermore, we apply the enhanced NAG method to implement homomorphic logistic regression training, achieving comparable performance within only four iterations. The proposed quadratic-gradient approach offers a unified framework that synergizes the advantages of first-order gradient methods and second-order Newton-type methods, suggesting broad applicability to diverse numerical optimization tasks.