Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiang, Xie, Qiaomin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916525202472960
author Li, Xiang
Xie, Qiaomin
author_facet Li, Xiang
Xie, Qiaomin
contents The convergence behavior of Stochastic Gradient Descent (SGD) crucially depends on the stepsize configuration. When using a constant stepsize, the SGD iterates form a Markov chain, enjoying fast convergence during the initial transient phase. However, when reaching stationarity, the iterates oscillate around the optimum without making further progress. In this paper, we study the convergence diagnostics for SGD with constant stepsize, aiming to develop an effective dynamic stepsize scheme. We propose a novel coupling-based convergence diagnostic procedure, which monitors the distance of two coupled SGD iterates for stationarity detection. Our diagnostic statistic is simple and is shown to track the transition from transience stationarity theoretically. We conduct extensive numerical experiments and compare our method against various existing approaches. Our proposed coupling-based stepsize scheme is observed to achieve superior performance across a diverse set of convex and non-convex problems. Moreover, our results demonstrate the robustness of our approach to a wide range of hyperparameters.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11341
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent
Li, Xiang
Xie, Qiaomin
Machine Learning
Optimization and Control
The convergence behavior of Stochastic Gradient Descent (SGD) crucially depends on the stepsize configuration. When using a constant stepsize, the SGD iterates form a Markov chain, enjoying fast convergence during the initial transient phase. However, when reaching stationarity, the iterates oscillate around the optimum without making further progress. In this paper, we study the convergence diagnostics for SGD with constant stepsize, aiming to develop an effective dynamic stepsize scheme. We propose a novel coupling-based convergence diagnostic procedure, which monitors the distance of two coupled SGD iterates for stationarity detection. Our diagnostic statistic is simple and is shown to track the transition from transience stationarity theoretically. We conduct extensive numerical experiments and compare our method against various existing approaches. Our proposed coupling-based stepsize scheme is observed to achieve superior performance across a diverse set of convex and non-convex problems. Moreover, our results demonstrate the robustness of our approach to a wide range of hyperparameters.
title Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2412.11341