Saved in:
Bibliographic Details
Main Authors: Wei, Ziyang, Zhu, Wanrong, Wu, Wei Biao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2307.06915
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915230096818176
author Wei, Ziyang
Zhu, Wanrong
Wu, Wei Biao
author_facet Wei, Ziyang
Zhu, Wanrong
Wu, Wei Biao
contents Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in different settings. In this paper, we explore a general averaging scheme for SGD. Specifically, we establish the asymptotic normality of a broad range of weighted averaged SGD solutions and provide asymptotically valid online inference approaches. Furthermore, we propose an adaptive averaging scheme that exhibits both optimal statistical rate and favorable non-asymptotic convergence, drawing insights from the optimal weight for the linear model in terms of non-asymptotic mean squared error (MSE).
format Preprint
id arxiv_https___arxiv_org_abs_2307_06915
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality
Wei, Ziyang
Zhu, Wanrong
Wu, Wei Biao
Machine Learning
Stochastic Gradient Descent (SGD) is one of the most popular algorithms in statistical and machine learning due to its computational and memory efficiency. Various averaging schemes have been proposed to accelerate the convergence of SGD in different settings. In this paper, we explore a general averaging scheme for SGD. Specifically, we establish the asymptotic normality of a broad range of weighted averaged SGD solutions and provide asymptotically valid online inference approaches. Furthermore, we propose an adaptive averaging scheme that exhibits both optimal statistical rate and favorable non-asymptotic convergence, drawing insights from the optimal weight for the linear model in terms of non-asymptotic mean squared error (MSE).
title Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality
topic Machine Learning
url https://arxiv.org/abs/2307.06915