中文
相关论文

相关论文: Last Iterate Risk Bounds of SGD with Decaying Step…

200 篇论文

Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in each updating step, and good performance. Standard excess…

机器学习 · 计算机科学 2021-05-14 Yi Xu , Qi Qian , Hao Li , Rong Jin

The non-asymptotic analysis of Stochastic Gradient Descent (SGD) typically yields bounds that decompose into a bias term and a variance term. In this work, we focus on the bias component and study the extent to which SGD can match the…

最优化与控制 · 数学 2026-02-02 Daniel Cortild , Lucas Ketels , Juan Peypouquet , Guillaume Garrigos

Stochastic Gradient Descent (SGD) is widely used in machine learning research. Previous convergence analyses of SGD under the vanishing step-size setting typically require Robbins-Monro conditions. However, in practice, a wider variety of…

机器学习 · 计算机科学 2025-04-18 Ruinan Jin , Difei Cheng , Hong Qiao , Xin Shi , Shaodong Liu , Bo Zhang

We propose a new framework, inspired by random matrix theory, for analyzing the dynamics of stochastic gradient descent (SGD) when both number of samples and dimensions are large. This framework applies to any fixed stepsize and the finite…

最优化与控制 · 数学 2021-02-09 Courtney Paquette , Kiwon Lee , Fabian Pedregosa , Elliot Paquette

Existing theory suggests that for linear regression problems categorized by capacity and source conditions, gradient descent (GD) is always minimax optimal, while both ridge regression and online stochastic gradient descent (SGD) are…

机器学习 · 统计学 2025-09-23 Jingfeng Wu , Peter L. Bartlett , Jason D. Lee , Sham M. Kakade , Bin Yu

Stochastic gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of problems. While the empirical success of SGD is often attributed to its computational efficiency…

机器学习 · 统计学 2022-06-16 Courtney Paquette , Elliot Paquette , Ben Adlam , Jeffrey Pennington

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

机器学习 · 统计学 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

Motivated by the recent successes of neural networks that have the ability to fit the data perfectly and generalize well, we study the noiseless model in the fundamental least-squares setup. We assume that an optimum predictor fits…

机器学习 · 计算机科学 2021-06-04 Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice, which has been hypothesized to play an important role in the generalization of modern machine learning approaches. In this work, we seek to…

机器学习 · 计算机科学 2022-07-12 Difan Zou , Jingfeng Wu , Vladimir Braverman , Quanquan Gu , Dean P. Foster , Sham M. Kakade

The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by…

最优化与控制 · 数学 2025-11-21 Fabio Nobile , Matteo Raviola , Nathan Schaeffer

Under mild assumptions stochastic gradient methods asymptotically achieve an optimal rate of convergence if the arithmetic mean of all iterates is returned as an approximate optimal solution. However, in the absence of stochastic noise, the…

最优化与控制 · 数学 2022-10-06 Melinda Hagedorn , Florian Jarre

It has repeatedly been observed that loss minimization by stochastic gradient descent (SGD) leads to heavy-tailed distributions of neural network parameters. Here, we analyze a continuous diffusion approximation of SGD, called homogenized…

机器学习 · 统计学 2024-02-05 Zhe Jiao , Martin Keller-Ressel

This paper theoretically reanalyzes the convergence of the mini-batch stochastic gradient descent (SGD) for a structured minimization problem involving a finite-sum function with its gradient being stochastically approximated, and an…

最优化与控制 · 数学 2026-04-07 Runze Li , Jintao Xu , Wenxun Xing

Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational…

机器学习 · 统计学 2025-08-25 Hao Chen , Lili Zheng , Raed Al Kontar , Garvesh Raskutti

Minimizing empirical risk subject to a set of constraints can be a useful strategy for learning restricted classes of functions, such as monotonic functions, submodular functions, classifiers that guarantee a certain class label for some…

机器学习 · 计算机科学 2016-10-26 Andrew Cotter , Maya Gupta , Jan Pfeifer

In this work we consider stochastic gradient descent (SGD) for solving linear inverse problems in Banach spaces. SGD and its variants have been established as one of the most successful optimisation methods in machine learning, imaging and…

机器学习 · 计算机科学 2023-02-13 Z. Kereta , B. Jin

A theoretical, and potentially also practical, problem with stochastic gradient descent is that trajectories may escape to infinity. In this note, we investigate uniform boundedness properties of iterates and function values along the…

机器学习 · 计算机科学 2022-06-23 Xiaoyu Wang , Mikael Johansson

We investigate the stochastic gradient descent (SGD) method where the step size lies within a banded region instead of being given by a fixed formula. The optimal convergence rate under mild conditions and large initial step size is proved.…

最优化与控制 · 数学 2023-04-10 Xiaoyu Wang , Ya-xiang Yuan

We give a new separation result between the generalization performance of stochastic gradient descent (SGD) and of full-batch gradient descent (GD) in the fundamental stochastic convex optimization model. While for SGD it is well-known that…

机器学习 · 计算机科学 2021-07-01 Idan Amir , Tomer Koren , Roi Livni

Stochastic Gradient Descent (SGD) is one of the many iterative optimization methods that are widely used in solving machine learning problems. These methods display valuable properties and attract researchers and industrial machine learning…

机器学习 · 计算机科学 2023-10-04 Farshed Abdukhakimov , Chulu Xiang , Dmitry Kamzolov , Martin Takáč