中文
相关论文

相关论文: Stability and Convergence of Stochastic Gradient C…

200 篇论文

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…

机器学习 · 计算机科学 2013-01-01 Ohad Shamir , Tong Zhang

Stochastic Gradient Descent (SGD) with gradient clipping is a powerful technique for enabling differentially private optimization. Although prior works extensively investigated clipping with a constant threshold, private training remains…

机器学习 · 计算机科学 2024-12-31 Egor Shulgin , Peter Richtárik

Distributed optimization plays an important role in modern large-scale machine learning and data processing systems by optimizing the utilization of computational resources. One of the classical and popular approaches is Local Stochastic…

最优化与控制 · 数学 2024-12-19 Andrey Sadchikov , Savelii Chezhegov , Aleksandr Beznosikov , Alexander Gasnikov

We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically. We show that the resulting method, per-sample clipped SGD (PS-Clip-SGD), achieves optimal…

最优化与控制 · 数学 2026-05-05 Davide Nobile , Philipp Grohs

SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automated stepsize that works well across a wide range of convex…

最优化与控制 · 数学 2024-02-22 Zachary Frangella , Pratik Rathore , Shipu Zhao , Madeleine Udell

Stochastic first-order methods such as Stochastic Extragradient (SEG) or Stochastic Gradient Descent-Ascent (SGDA) for solving smooth minimax problems and, more generally, variational inequality problems (VIP) have been gaining a lot of…

Stochastic gradient descent (SGD) is a powerful optimization technique that is particularly useful in online learning scenarios. Its convergence analysis is relatively well understood under the assumption that the data samples are…

机器学习 · 计算机科学 2024-10-03 Ethan Che , Jing Dong , Xin T. Tong

Stochastic gradient descent (SGD) and its variants are widely used and highly effective optimization methods in machine learning, especially for neural network training. By using a single datum or a small subset of the data, selected…

数值分析 · 数学 2026-01-21 Bangti Jin , Zeljko Kereta , Yuxin Xia

The success of modern machine learning is due in part to the adaptive optimization methods that have been developed to deal with the difficulties of training large models over complex datasets. One such method is gradient clipping: a…

机器学习 · 统计学 2024-10-08 Noah Marshall , Ke Liang Xiao , Atish Agarwala , Elliot Paquette

We study nonlinearly preconditioned gradient methods for smooth nonconvex optimization problems, focusing on sigmoid preconditioners that inherently perform a form of gradient clipping akin to the widely used gradient clipping technique.…

最优化与控制 · 数学 2025-10-14 Konstantinos Oikonomidis , Jan Quan , Panagiotis Patrinos

Adaptive gradient methods, such as AdaGrad, are among the most successful optimization algorithms for neural network training. While these methods are known to achieve better dimensional dependence than stochastic gradient descent (SGD) for…

最优化与控制 · 数学 2025-06-09 Ruichen Jiang , Devyani Maladkar , Aryan Mokhtari

We present a unified theorem for the convergence analysis of stochastic gradient algorithms for minimizing a smooth and convex loss plus a convex regularizer. We do this by extending the unified analysis of Gorbunov, Hanzely \& Richt\'arik…

机器学习 · 计算机科学 2020-06-23 Ahmed Khaled , Othmane Sebbouh , Nicolas Loizou , Robert M. Gower , Peter Richtárik

Stochastic gradient descent (SGD) is the main algorithm behind a large body of work in machine learning. In many cases, constraints are enforced via projections, leading to projected stochastic gradient algorithms. In recent years, a large…

最优化与控制 · 数学 2025-10-06 Yuping Zheng , Andrew Lamperski

For finite-dimensional problems, stochastic approximation methods have long been used to solve stochastic optimization problems. Their application to infinite-dimensional problems is less understood, particularly for nonconvex objectives.…

最优化与控制 · 数学 2021-01-14 Caroline Geiersbach , Teresa Scarinci

Stochastic gradient descent (SGD) is a popular and efficient method with wide applications in training deep neural nets and other nonconvex models. While the behavior of SGD is well understood in the convex learning setting, the existing…

机器学习 · 计算机科学 2019-12-16 Yunwen Lei , Ting Hu , Guiying Li , Ke Tang

Stochastic gradient algorithms are the main focus of large-scale optimization problems and led to important successes in the recent advancement of the deep learning algorithms. The convergence of SGD depends on the careful choice of…

机器学习 · 计算机科学 2017-03-03 Caglar Gulcehre , Jose Sotelo , Marcin Moczulski , Yoshua Bengio

This paper analyzes the trajectories of stochastic gradient descent (SGD) to help understand the algorithm's convergence properties in non-convex problems. We first show that the sequence of iterates generated by SGD remains bounded and…

最优化与控制 · 数学 2020-06-22 Panayotis Mertikopoulos , Nadav Hallak , Ali Kavis , Volkan Cevher

We study to what extent may stochastic gradient descent (SGD) be understood as a "conventional" learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex…

机器学习 · 计算机科学 2023-01-13 Tomer Koren , Roi Livni , Yishay Mansour , Uri Sherman

Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- common in modern machine learning and reinforcement learning -- remains poorly understood. In this…

最优化与控制 · 数学 2025-08-08 Ilyas Fatkhullin , Florian Hübler , Guanghui Lan

We show that parametric models trained by a stochastic gradient method (SGM) with few iterations have vanishing generalization error. We prove our results by arguing that SGM is algorithmically stable in the sense of Bousquet and Elisseeff.…

机器学习 · 计算机科学 2016-02-09 Moritz Hardt , Benjamin Recht , Yoram Singer