中文
相关论文

相关论文: Convergence, Sticking and Escape: Stochastic Dynam…

200 篇论文

We show that stochastic gradient descent (SGD) escapes from sharp minima exponentially fast even before SGD reaches stationary distribution. SGD has been a de-facto standard training algorithm for various machine learning tasks. However,…

机器学习 · 计算机科学 2022-03-22 Hikaru Ibayashi , Masaaki Imaizumi

In this paper, we provide a theoretical study of noise geometry for minibatch stochastic gradient descent (SGD), a phenomenon where noise aligns favorably with the geometry of local landscape. We propose two metrics, derived from analyzing…

机器学习 · 计算机科学 2024-02-02 Mingze Wang , Lei Wu

Stochastic gradient descent (SGD) and its variants are mainstream methods to train deep neural networks. Since neural networks are non-convex, more and more works study the dynamic behavior of SGD and the impact to its generalization,…

机器学习 · 计算机科学 2020-10-13 Qi Meng , Shiqi Gong , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

Previous works on stochastic gradient descent (SGD) often focus on its success. In this work, we construct worst-case optimization problems illustrating that, when not in the regimes that the previous works often assume, SGD can exhibit…

机器学习 · 计算机科学 2023-05-30 Liu Ziyin , Botao Li , James B. Simon , Masahito Ueda

This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD) with non-increasing step sizes. First, we show that the recursion defining SGD can be provably approximated by solutions of a time inhomogeneous…

最优化与控制 · 数学 2021-02-02 Xavier Fontaine , Valentin De Bortoli , Alain Durmus

Stochastic gradient descent (SGD) is widely used in machine learning. Although being commonly viewed as a fast but not accurate version of gradient descent (GD), it always finds better solutions than GD for modern neural networks. In order…

机器学习 · 计算机科学 2018-08-17 Robert Kleinberg , Yuanzhi Li , Yang Yuan

Stochastic gradient descent (SGD) with mini-batching is a standard tool in large-scale optimization, yet its theoretical properties under heavy-tailed gradient noise remain largely unexplored. In this paper we study SGD with increasing…

概率论 · 数学 2026-05-11 Bartosz Glowacki , Rafal Kulik , Philippe Soulier

In centralized settings, it is well known that stochastic gradient descent (SGD) avoids saddle points and converges to local minima in nonconvex problems. However, similar guarantees are lacking for distributed first-order algorithms. The…

最优化与控制 · 数学 2022-03-07 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general form of gradient based optimization dynamics with unbiased…

机器学习 · 统计学 2019-06-11 Zhanxing Zhu , Jingfeng Wu , Bing Yu , Lei Wu , Jinwen Ma

We study the Stochastic Gradient Descent (SGD) method in nonconvex optimization problems from the point of view of approximating diffusion processes. We prove rigorously that the diffusion process can approximate the SGD algorithm weakly…

机器学习 · 统计学 2018-03-06 Wenqing Hu , Chris Junchi Li , Lei Li , Jian-Guo Liu

In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus…

机器学习 · 统计学 2021-06-14 Kangqiao Liu , Liu Ziyin , Masahito Ueda

In machine learning, stochastic gradient descent (SGD) is widely deployed to train models using highly non-convex objectives with equally complex noise models. Unfortunately, SGD theory often makes restrictive assumptions that fail to…

机器学习 · 计算机科学 2022-10-11 Vivak Patel , Shushu Zhang , Bowen Tian

Inverse problems in scientific computing often require optimization over infinite-dimensional Hilbert spaces. A commonly used solver in such settings is stochastic gradient descent (SGD), where gradients are approximated using randomly…

最优化与控制 · 数学 2026-04-14 Sandra Cerrai , Qin Li , Anjali Nair , Jaeyoung Yoon

In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of…

机器学习 · 计算机科学 2025-05-13 Davide Barbieri , Matteo Bonforte , Peio Ibarrondo

We study the scaling limits of stochastic gradient descent (SGD) with constant step-size in the high-dimensional regime. We prove limit theorems for the trajectories of summary statistics (i.e., finite-dimensional functions) of SGD as the…

机器学习 · 统计学 2023-08-21 Gerard Ben Arous , Reza Gheissari , Aukosh Jagannath

In this article, we consider convergence of stochastic gradient descent schemes (SGD), including momentum stochastic gradient descent (MSGD), under weak assumptions on the underlying landscape. More explicitly, we show that on the event…

机器学习 · 计算机科学 2024-11-20 Steffen Dereich , Sebastian Kassing

In this paper, we examine the time it takes for stochastic gradient descent (SGD) to reach the global minimum of a general, non-convex loss function. We approach this question through the lens of randomly perturbed dynamical systems and…

最优化与控制 · 数学 2025-06-10 Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

Stochastic gradient descent (SGD) is central to deep learning, yet the dynamical origin of its preference for flatter, more generalizable solutions remains unclear. Here, by analyzing SGD learning dynamics, we identify a nonequilibrium…

机器学习 · 计算机科学 2026-01-19 Ning Yang , Yikuan Zhang , Qi Ouyang , Chao Tang , Yuhai Tu

Stochastic Gradient Descent (SGD) is a widely deployed optimization procedure throughout data-driven and simulation-driven disciplines, which has drawn a substantial interest in understanding its global behavior across a broad class of…

最优化与控制 · 数学 2021-04-02 Vivak Patel , Shushu Zhang

Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…

分布式、并行与集群计算 · 计算机科学 2018-06-25 Dan Alistarh , Christopher De Sa , Nikola Konstantinov
‹ 上一页 1 2 3 10 下一页 ›