Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification

• URL: http://arxiv.org/abs/2608.06250v1
• Date: Thu, 06 Aug 2026 16:41:00 GMT
• Title: Minimax Optimal Early-Stopped Gradient Descent for Gaussian Mixture Classification
• Abstract summary: Training data can be linearly separable even when the underlying distribution is not.<n>We show that early stopping can overcome this suboptimality.<n>A new calibration result converts excess logistic risk into excess zero-one risk.
• Score: 8.717253904965371
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In overparameterised classification, training data can be linearly separable even when the underlying distribution is not. In this setting, gradient descent (GD) on the logistic loss diverges in norm while converging in direction to a max-margin interpolating classifier, whose implicit bias can be statistically suboptimal. In this work, we show that early stopping can overcome this suboptimality: in a Gaussian mixture model with label-flipping noise, GD stopped at an appropriate oracle time achieves minimax-optimal excess zero-one risk for covariance spectra with fast and continuous decay, including polynomial and exponential spectral decays. Our analysis combines a sharp upper bound for the early-stopped iterate with a matching statistical lower bound over arbitrary classifiers, yielding optimal rates that are validated by experiments. A central technical contribution is a new calibration result that converts excess logistic risk into excess zero-one risk; it handles the model misspecification induced by the label-flipping noise, and removes the square-root rate in standard bounds. We also establish a lower bound for linear interpolators, showing that interpolation can require exponentially more samples than early stopping to achieve the same excess risk.

Related papers

• The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimization [50.59470683896735]
  min-max optimization has attracted increasing attention due to its applications in modern machine learning.<n>We provide a comprehensive theoretical of gradient descent (SGDA)<n>We develop new clipping-free algorithms, i.e., Stoc-GDAM and Stoc-TRmax, and they both can achieve the optimal dependence on the target accuracy without using gradient clipping.
  arXiv  Detail & Related papers  (2026-09-05T12:49:28Z)
• Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression [11.223656960922478]
  We study variance-preserving diffusion of the response in mixed linear regression (MLR) with unknown mixing weights.<n>Our analysis separates the statistical guarantees of score matching from the loss geometry and optimization signal at a fixed diffusion noise level.
  arXiv  Detail & Related papers  (2026-09-04T19:52:26Z)
• Graph-based Clustering Revisited: A Relaxation of Kernel $k$-Means Perspective [73.18641268511318]
  We propose a graph-based clustering algorithm that only relaxes the orthonormal constraint to derive clustering results.<n>To ensure a doubly constraint into a gradient, we transform the non-negative constraint into a class probability parameter.
  arXiv  Detail & Related papers  (2025-09-23T09:14:39Z)
• Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise [60.92029979853314]
  We investigate the roles of gradient normalization and clipping in ensuring the convergence of Gradient Descent (SGD) under heavy-tailed noise. Our work provides the first theoretical evidence demonstrating the benefits of gradient normalization in SGD under heavy-tailed noise. We introduce an accelerated SGD variant incorporating gradient normalization and clipping, further enhancing convergence rates under heavy-tailed noise.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)
• High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise [59.25598762373543]
  We show that wetailed high-prob convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. We demonstrate analytically and that $ta$ can be used to the preferred choice of setting for a given problem.
  arXiv  Detail & Related papers  (2023-10-28T18:53:41Z)
• Distributionally Robust Optimization with Bias and Variance Reduction [9.341215359733601]
  We show that Prospect, a gradient-based algorithm, enjoys linear convergence for smooth regularized losses. We also show that Prospect can converge 2-3$times$ faster than baselines such as gradient-based methods.
  arXiv  Detail & Related papers  (2023-10-21T00:03:54Z)
• Max-affine regression via first-order methods [7.12511675782289]
  The max-affine model ubiquitously arises in applications in signal processing and statistics. We present a non-asymptotic convergence analysis of gradient descent (GD) and mini-batch gradient descent (SGD) for max-affine regression.
  arXiv  Detail & Related papers  (2023-08-15T23:46:44Z)
• Batches Stabilize the Minimum Norm Risk in High Dimensional Overparameterized Linear Regression [12.443289202402761]
  We show the benefits of batch- partitioning through the lens of a minimum-norm overparametrized linear regression model. We characterize the optimal batch size and show it is inversely proportional to the noise level. We also show that shrinking the batch minimum-norm estimator by a factor equal to the Weiner coefficient further stabilizes it and results in lower quadratic risk in all settings.
  arXiv  Detail & Related papers  (2023-06-14T11:02:08Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• Minimax Supervised Clustering in the Anisotropic Gaussian Mixture Model: A new take on Robust Interpolation [5.98367009147573]
  We study the supervised clustering problem under the two-component anisotropic Gaussian mixture model. We show that in the high-dimensional regime, the linear discriminant analysis (LDA) classifier turns out to be sub-optimal in the minimax sense.
  arXiv  Detail & Related papers  (2021-11-13T05:19:37Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime [16.1176305285103]
  We prove bounds on the population risk of the maximum margin algorithm for two-class linear classification. We analyze this algorithm applied to random data including misclassification noise.
  arXiv  Detail & Related papers  (2020-04-25T00:06:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.