中文
相关论文

相关论文: Near-Optimal Decentralized Stochastic Nonconvex Op…

200 篇论文

Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based…

最优化与控制 · 数学 2019-10-29 Sulaiman A. Alghunaim , Kun Yuan , Ali H. Sayed

Distributed Optimization is an increasingly important subject area with the rise of multi-agent control and optimization. We consider a decentralized stochastic optimization problem where the agents on a graph aim to asynchronously optimize…

最优化与控制 · 数学 2021-10-22 Vyacheslav Kungurtsev , Mahdi Morafah , Tara Javidi , Gesualdo Scutari

Decentralized optimization with time-varying networks is an emerging paradigm in machine learning. It saves remarkable communication overhead in large-scale deep training and is more robust in wireless scenarios especially when nodes are…

机器学习 · 计算机科学 2022-11-02 Xinmeng Huang , Kun Yuan

We study the distributed stochastic compositional optimization problems over directed communication networks in which agents privately own a stochastic compositional objective function and collaborate to minimize the sum of all objective…

最优化与控制 · 数学 2022-03-22 Shengchao Zhao , Yongchao Liu

Recently, the study of heavy-tailed noises in first-order nonconvex stochastic optimization has gotten a lot of attention since it was recognized as a more realistic condition as suggested by many empirical observations. Specifically, the…

最优化与控制 · 数学 2025-05-30 Zijian Liu , Zhengyuan Zhou

The empirical evidence indicates that stochastic optimization with heavy-tailed gradient noise is more appropriate to characterize the training of machine learning models than that with standard bounded gradient variance noise. Most…

机器学习 · 计算机科学 2026-01-28 Hongxu Chen , Ke Wei , Xiaoming Yuan , Luo Luo

This paper considers the smooth bilevel optimization in which the lower-level problem is strongly convex and the upper-level problem is possibly nonconvex. We focus on the stochastic setting where the algorithm can access the unbiased…

机器学习 · 计算机科学 2025-12-16 Zhuanghua Liu , Luo Luo

We study convex composite optimization problems, where the objective function is given by the sum of a prox-friendly function and a convex function whose subgradients are estimated under heavy-tailed noise. Existing work often employs…

最优化与控制 · 数学 2025-10-14 Chuan He , Zhaosong Lu

In this paper, we design two compressed decentralized algorithms for solving nonconvex stochastic optimization under two different scenarios. Both algorithms adopt a momentum technique to achieve fast convergence and a message-compression…

To understand the convergence behavior of the Push-Pull method for decentralized optimization with stochastic gradients (Stochastic Push-Pull), this paper presents a comprehensive analysis. Specifically, we first clarify the algorithm's…

最优化与控制 · 数学 2025-06-10 Runze You , Shi Pu

The graduated optimization approach is a method for finding global optimal solutions for nonconvex functions by using a function smoothing operation with stochastic noise. This paper makes three contributions regarding graduated…

机器学习 · 计算机科学 2026-01-27 Naoki Sato , Hideaki Iiduka

Decentralized stochastic optimization has emerged as a fundamental paradigm for large-scale machine learning. However, practical implementations often rely on biased gradient estimators arising from communication compression or inexact…

最优化与控制 · 数学 2026-04-10 Qing Xu , Yiwei Liao , Wenqi Fan , Xingxing You , Songyi Dian

Decentralized methods to solve finite-sum minimization problems are important in many signal processing and machine learning tasks where the data is distributed over a network of nodes and raw data sharing is not permitted due to privacy…

机器学习 · 计算机科学 2020-02-14 Ran Xin , Soummya Kar , Usman A. Khan

In this paper, we propose a new way to obtain optimal convergence rates for smooth stochastic (strong) convex optimization tasks. Our approach is based on results for optimization tasks where gradients have nonrandom noise. In contrast to…

最优化与控制 · 数学 2020-04-16 Darina Dvinskikh , Alexander Tyurin , Alexander Gasnikov , Sergey Omelchenko

Privacy protection and nonconvexity are two challenging problems in decentralized optimization and learning involving sensitive data. Despite some recent advances addressing each of the two problems separately, no results have been reported…

最优化与控制 · 数学 2022-12-16 Yongqiang Wang , Tamer Basar

We study non-smooth stochastic decentralized optimization problems over time-varying networks, where objective functions are distributed across nodes and network connections may intermittently appear or break. Specifically, we consider two…

最优化与控制 · 数学 2026-04-28 Maxim Divilkovskiy , Alexander Gasnikov

In this paper, we provide novel optimal (or near optimal) convergence rates for a clipped version of the stochastic subgradient method. We consider nonsmooth convex problems over possibly unbounded domains, under heavy-tailed noise that…

最优化与控制 · 数学 2025-04-21 Daniela Angela Parletta , Andrea Paudice , Saverio Salzo

Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order methods can significantly accelerate convergence in…

最优化与控制 · 数学 2025-10-14 Abdurakhmon Sadiev , Peter Richtárik , Ilyas Fatkhullin

Recent empirical evidence indicates that many machine learning applications involve heavy-tailed gradient noise, which challenges the standard assumptions of bounded variance in stochastic optimization. Gradient clipping has emerged as a…

最优化与控制 · 数学 2025-07-10 Florian Hübler , Ilyas Fatkhullin , Niao He

Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity. However, three fundamental challenges in…

机器学习 · 计算机科学 2021-05-20 Xin Zhang , Jia Liu , Zhengyuan Zhu , Elizabeth S. Bentley