中文
相关论文

相关论文: Beyond Uniform Smoothness: A Stopped Analysis of A…

200 篇论文

Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms…

机器学习 · 计算机科学 2025-05-09 Michael Crawshaw , Mingrui Liu

Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness…

Classical convergence analyses for optimization algorithms rely on the widely-adopted uniform smoothness assumption. However, recent experimental studies have demonstrated that many machine learning problems exhibit non-uniform smoothness,…

机器学习 · 计算机科学 2024-09-27 Zhenyu Sun , Ermin Wei

Stochastic non-smooth convex optimization constitutes a class of problems in machine learning and operations research. This paper considers minimization of a non-smooth function based on stochastic subgradients. When the function has a…

最优化与控制 · 数学 2016-07-12 Sucha Supittayapornpong , Michael J. Neely

This paper is devoted to the study of stochastic optimization problems under the generalized smoothness assumption. By considering the unbiased gradient oracle in Stochastic Gradient Descent, we provide strategies to achieve in bounds the…

最优化与控制 · 数学 2025-05-26 Aleksandr Lobanov , Alexander Gasnikov

We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient…

机器学习 · 计算机科学 2022-06-07 Alexander Tyurin , Lukang Sun , Konstantin Burlachenko , Peter Richtárik

We study stochastic gradient descent (SGD) with gradient clipping on convex functions under a generalized smoothness assumption called $(L_0,L_1)$-smoothness. Using gradient clipping, we establish a high probability convergence rate that…

最优化与控制 · 数学 2025-06-04 Ofir Gaash , Kfir Yehuda Levy , Yair Carmon

We study the optimization of non-convex functions that are not necessarily smooth (gradient and/or Hessian are Lipschitz) using first order methods. Smoothness is a restrictive assumption in machine learning in both theory and practice,…

最优化与控制 · 数学 2025-06-27 Daniel Yiming Cao , August Y. Chen , Karthik Sridharan , Benjamin Tang

The generalized smooth condition, $(L_{0},L_{1})$-smoothness, has triggered people's interest since it is more realistic in many optimization problems shown by both empirical and theoretical evidence. Two recent works established the…

机器学习 · 计算机科学 2023-10-31 Zijian Liu , Srikanth Jagabathula , Zhengyuan Zhou

We study gradient methods for optimizing $(L_0, L_1)$-smooth functions, a class that generalizes Lipschitz-smooth functions and has gained attention for its relevance in machine learning. We provide new insights into the structure of this…

最优化与控制 · 数学 2025-03-11 Daniil Vankov , Anton Rodomanov , Angelia Nedich , Lalitha Sankar , Sebastian U. Stich

This paper considers the nonconvex nonsmooth problem in which the objective function is Lipschitz continuous. We focus on the stochastic setting where the algorithm can access stochastic function value evaluations with heavy-tailed noise,…

机器学习 · 计算机科学 2026-05-26 Zhuanghua Liu , Luo Luo

We study first-order methods for convex optimization problems with functions $f$ satisfying the recently proposed $\ell$-smoothness condition $||\nabla^{2}f(x)|| \le \ell\left(||\nabla f(x)||\right),$ which generalizes the $L$-smoothness…

最优化与控制 · 数学 2026-05-22 Alexander Tyurin

Large-scale nonconvex optimization problems are ubiquitous in modern machine learning, and among practitioners interested in solving them, Stochastic Gradient Descent (SGD) reigns supreme. We revisit the analysis of SGD in the nonconvex…

最优化与控制 · 数学 2020-07-27 Ahmed Khaled , Peter Richtárik

Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by using stochastic gradient descent (SGD), theoretical analysis…

机器学习 · 计算机科学 2022-02-21 Harsh Vardhan , Sebastian U. Stich

We study fundamental limits of first-order stochastic optimization in a range of nonconvex settings, including L-smooth functions satisfying Quasar-Convexity (QC), Quadratic Growth (QG), and Restricted Secant Inequalities (RSI). While the…

机器学习 · 统计学 2025-06-03 El Mehdi Saad , Wei-Cheng Lee , Francesco Orabona

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

$L_0$-smoothness, which has been pivotal to advancing decentralized optimization theory, is often fairly restrictive for modern tasks like deep learning. The recent advent of relaxed $(L_0,L_1)$-smoothness condition enables improved…

最优化与控制 · 数学 2025-08-13 Zhanhong Jiang , Aditya Balu , Soumik Sarkar

We propose an adaptive accelerated smoothing technique for a nonsmooth convex optimization problem where the smoothing update rule is coupled with the momentum parameter. We also extend the setting to the case where the objective function…

最优化与控制 · 数学 2026-04-21 Reza Rahimi Baghbadorani , Sergio Grammatico , Peyman Mohajerin Esfahani

In this paper, we address stochastic optimization problems involving a composition of a non-smooth outer function and a smooth inner function, a formulation frequently encountered in machine learning and operations research. To deal with…

最优化与控制 · 数学 2026-05-15 Tommaso Giovannelli , Jingfu Tan , Luis Nunes Vicente

This paper addresses stochastic optimization of Lipschitz-continuous, nonsmooth and nonconvex objectives over compact convex sets, where only noisy function evaluations are available. While gradient-free methods have been developed for…

最优化与控制 · 数学 2025-08-26 Anik Kumar Paul , Shalabh Bhatnagar
‹ 上一页 1 2 3 10 下一页 ›