Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics

• URL: http://arxiv.org/abs/2608.04382v1
• Date: Wed, 05 Aug 2026 02:39:49 GMT
• Title: Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics
• Abstract summary: Implicit bias emerging from machine learning often prevents from overfitting to spurious patterns.<n>This work aims to understand the mechanism of this early-stage alignment phenomenon.
• Score: 3.7628827026898466
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gradient descent has been of particular interest in modern machine learning beyond sole focus on optimization. Implicit bias emerging from optimization, though not being encoded by the learning objective, often prevents from overfitting to spurious patterns. A typical instance is the max-margin implicit bias of a linear classifier, widely established for exponentially tailed loss functions. Even after having a given dataset separated, the parameter vector continues to evolve towards the max-margin direction asymptotically along the gradient descent dynamics. This phenomenon corroborates a frequent empirical observation of "train longer, generalize better." However, the max-margin convergence is an asymptotic phenomenon, and what is worse, this asymptotic convergence rate is significantly slower than pure convex optimization. Even so, the parameter vector along gradient descent dynamics commonly correlates with the max-margin direction positively (though not exactly) within considerably fewer iterations than the asymptotic rate. By shedding another light on this classical problem, this work aims to understand the mechanism of this early-stage alignment phenomenon. Our theoretical results demonstrate that the parameter vector weakly aligns with the max-margin direction within $O(\exp(\exp(-δ)))$ iterations, where $δ>0$ is the permissible alignment error, which is shown to be tight. By tracking the radial and tangential flows, our proof operates on the alignment dynamics directly with dataset geometry and gets rid of the asymptotic expansion, which is a key insight to establishing faster weak alignment.

Related papers

• High-dimensional Limit of SGD for Diagonal Linear Networks [20.199898128645497]
  We show that gradient descent on diagonal linear networks is well-approximated by continuous dynamics governed by a differential equation (SDE)<n>We show that, under a suitable parametrization, the 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.
  arXiv  Detail & Related papers  (2026-05-16T22:26:59Z)
• On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes [15.63629978994481]
  We present the first comprehensive theoretical analysis of this gradient cascade setting.<n>We identify conditions under which perturbations do not deteriorate the gradient convergence order.
  arXiv  Detail & Related papers  (2026-02-24T07:47:15Z)
• Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations [57.179679246370114]
  We identify the distribution of random perturbations that minimizes the estimator's variance as the perturbation stepsize tends to zero.<n>Our findings reveal that such desired perturbations can align directionally with the true gradient, instead of maintaining a fixed length.
  arXiv  Detail & Related papers  (2025-10-22T19:06:39Z)
• Long-time dynamics and universality of nonconvex gradient descent [0.7614628596146601]
  This paper develops a general approach to characterize the long-time behavior of non gradient descent in single-index models.<n>Our approach reveals that gradient descents are in general approximately independent of the data and strongly incoherent with the feature vectors.
  arXiv  Detail & Related papers  (2025-09-14T20:36:18Z)
• Implicit Bias and Fast Convergence Rates for Self-attention [26.766649949420746]
  We study the fundamental optimization principles of self-attention, the defining mechanism of transformers.<n>We analyze the implicit bias of gradient-baseds in a self-attention layer with a decoder in a linear classification.
  arXiv  Detail & Related papers  (2024-02-08T15:15:09Z)
• Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult [49.8719617899285]
  Large learning rates, when applied to objective descent for non optimization, yield various implicit biases including the edge of stability. This paper provides an initial step in descent and shows that these implicit biases are in fact various tips same iceberg.
  arXiv  Detail & Related papers  (2023-10-26T01:11:17Z)
• Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability [69.01076284478151]
  In machine learning optimization, gradient descent (GD) often operates at the edge of stability (EoS) This paper studies the convergence and implicit bias of constant-stepsize GD for logistic regression on linearly separable data in the EoS regime.
  arXiv  Detail & Related papers  (2023-05-19T16:24:47Z)
• Proximal Subgradient Norm Minimization of ISTA and FISTA [8.261388753972234]
  We show that the squared proximal subgradient norm for the class of iterative shrinkage-thresholding algorithms converges at an inverse square rate. We also show that the squared proximal subgradient norm for the class of faster iterative shrinkage-thresholding algorithms (FISTA) is accelerated to convergence at an inverse cubic rate.
  arXiv  Detail & Related papers  (2022-11-03T06:50:19Z)
• 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)
• Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate [105.62979485062756]
  This paper attempts to characterize the particular regularization effect of SGD in the moderate learning rate regime. We show that SGD converges along the large eigenvalue directions of the data matrix, while GD goes after the small eigenvalue directions.
  arXiv  Detail & Related papers  (2020-11-04T21:07:52Z)
• On Learning Rates and Schr\"odinger Operators [105.32118775014015]
  We present a general theoretical analysis of the effect of the learning rate. We find that the learning rate tends to zero for a broad non- neural class functions.
  arXiv  Detail & Related papers  (2020-04-15T09:52:37Z)

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.