High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yuchen, Lu, Kaihong, Wang, Long
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908412431826944
author Yang, Yuchen
Lu, Kaihong
Wang, Long
author_facet Yang, Yuchen
Lu, Kaihong
Wang, Long
contents In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this problem, a distributed clipped stochastic gradient descent algorithm is proposed, and the high probability convergence of the algorithm is studied. Existing works on distributed algorithms involving stochastic gradients only consider the light-tailed noises. Different from them, we study the case with heavy-tailed settings. Under mild assumptions on the graph connectivity, we prove that the algorithm converges in high probability under a certain clipping operator. Finally, a simulation is provided to demonstrate the effectiveness of our theoretical results
format Preprint
id arxiv_https___arxiv_org_abs_2506_11647
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise
Yang, Yuchen
Lu, Kaihong
Wang, Long
Optimization and Control
In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this problem, a distributed clipped stochastic gradient descent algorithm is proposed, and the high probability convergence of the algorithm is studied. Existing works on distributed algorithms involving stochastic gradients only consider the light-tailed noises. Different from them, we study the case with heavy-tailed settings. Under mild assumptions on the graph connectivity, we prove that the algorithm converges in high probability under a certain clipping operator. Finally, a simulation is provided to demonstrate the effectiveness of our theoretical results
title High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise
topic Optimization and Control
url https://arxiv.org/abs/2506.11647