English
Related papers

Related papers: Constant Stepsize Local GD for Logistic Regression…

200 papers

Stochastic gradient descent (SGD) is a workhorse algorithm for solving large-scale optimization problems in data science and machine learning. Understanding the convergence of SGD is hence of fundamental importance. In this work we examine…

Numerical Analysis · Mathematics 2024-12-11 Lehan Chen , Yuji Nakatsukasa

An usual problem in statistics consists in estimating the minimizer of a convex function. When we have to deal with large samples taking values in high dimensional spaces, stochastic gradient algorithms and their averaged versions are…

Statistics Theory · Mathematics 2022-01-12 Antoine Godichon-Baggioni

We study the gradient descent (GD) dynamics of a depth-2 linear neural network with a single input and output. We show that GD converges at an explicit linear rate to a global minimum of the training loss, even with a large stepsize --…

Machine Learning · Computer Science 2025-01-22 Pierfrancesco Beneventano , Blake Woodworth

We begin by briefly surveying some results on the convergence of the Stochastic Gradient Descent (SGD) Method, proved in a companion paper by the present authors. These results are based on viewing SGD as a version of Stochastic…

Machine Learning · Statistics 2025-09-10 Rajeeva L. Karandikar , M. Vidyasagar

Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness…

Machine Learning · Computer Science 2013-01-01 Ohad Shamir , Tong Zhang

An increasing number of machine learning problems, such as robust or adversarial variants of existing algorithms, require minimizing a loss function that is itself defined as a maximum. Carrying a loop of stochastic gradient ascent (SGA)…

Machine Learning · Computer Science 2021-11-29 Othmane Sebbouh , Marco Cuturi , Gabriel Peyré

In this paper, a new theory is developed for first-order stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal…

Optimization and Control · Mathematics 2020-05-07 Yi Xu , Qihang Lin , Tianbao Yang

This paper studies a class of distributed optimization algorithms by a set of agents, where each agent has only access to its own local convex objective function, and jointly minimizes the sum of the functions. The communications among…

Optimization and Control · Mathematics 2016-11-11 Qingguo Lü , Huaqing Li

We present a theoretical analysis of stochastic optimization methods in terms of their sensitivity with respect to the step size. We identify a key quantity that, for each method, describes how the performance degrades as the step size…

Optimization and Control · Mathematics 2026-05-27 Fabian Schaipp , Robert M. Gower , Adrien Taylor

We study a one-dimensional spatial population model where the population sizes at each site are chosen according to a translation invariant and ergodic distribution and are uniformly bounded away from 0 and infinity. We suppose that the…

Probability · Mathematics 2019-06-14 Raphaël Forien

We consider the minimization of an objective function given access to unbiased estimates of its gradient through stochastic gradient descent (SGD) with constant step-size. While the detailed analysis was only performed for quadratic…

Machine Learning · Statistics 2018-04-12 Aymeric Dieuleveut , Alain Durmus , Francis Bach

Previous studies on two-timescale stochastic approximation (SA) mainly focused on bounding mean-squared errors under diminishing stepsize schemes. In this work, we investigate {\it constant} stpesize schemes through the lens of Markov…

Systems and Control · Electrical Eng. & Systems 2025-02-25 Jeongyeol Kwon , Luke Dotson , Yudong Chen , Qiaomin Xie

We analyse the privacy leakage of noisy stochastic gradient descent by modeling R\'enyi divergence dynamics with Langevin diffusions. Inspired by recent work on non-stochastic algorithms, we derive similar desirable properties in the…

Machine Learning · Statistics 2022-02-08 Théo Ryffel , Francis Bach , David Pointcheval

In recent literature, a general two step procedure has been formulated for solving the problem of phase retrieval. First, a spectral technique is used to obtain a constant-error initial estimate, following which, the estimate is refined to…

Machine Learning · Statistics 2023-07-10 Yan Shuo Tan , Roman Vershynin

When training neural networks with full-batch gradient descent (GD) and step size $\eta$, the largest eigenvalue of the Hessian -- the sharpness $S(\boldsymbol{\theta})$ -- rises to $2/\eta$ and hovers there, a phenomenon termed the Edge of…

Machine Learning · Computer Science 2026-04-24 Fangshuo Liao , Afroditi Kolomvaki , Anastasios Kyrillidis

Can we accelerate convergence of gradient descent without changing the algorithm -- just by carefully choosing stepsizes? Surprisingly, we show that the answer is yes. Our proposed Silver Stepsize Schedule optimizes strongly convex…

Optimization and Control · Mathematics 2025-03-31 Jason M. Altschuler , Pablo A. Parrilo

This work establishes a rigorous connection between stability properties of discrete-time algorithms (DTAs) and corresponding continuous-time dynamical systems derived through $ O(s^r) $-resolution ordinary differential equations (ODEs). We…

Optimization and Control · Mathematics 2026-03-03 Amir Ali Farzin , Yuen-Man Pun , Philipp Braun , Iman Shames

We provide a new analysis of local SGD, removing unnecessary assumptions and elaborating on the difference between two data regimes: identical and heterogeneous. In both cases, we improve the existing theory and provide values of the…

Machine Learning · Computer Science 2022-04-18 Ahmed Khaled , Konstantin Mishchenko , Peter Richtárik

This paper proposes a novel CTA (Combine-Then-Adapt)-based decentralized algorithm for solving convex composite optimization problems over undirected and connected networks. The local loss function in these problems contains both smooth and…

Optimization and Control · Mathematics 2023-03-07 Luyao Guo , Xinli Shi , Jinde Cao , Zihao Wang

We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and examine the last iterate convergence. By now, it is known that standard stepsize choices…

Optimization and Control · Mathematics 2026-04-16 Guy Kornowski , Ohad Shamir