Saved in:
Bibliographic Details
Main Author: He, Chuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.14488
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910906153172992
author He, Chuan
author_facet He, Chuan
contents In this paper, we consider an unconstrained stochastic optimization problem where the objective function exhibits high-order smoothness. Specifically, we propose a new stochastic first-order method (SFOM) with multi-extrapolated momentum, in which multiple extrapolations are performed in each iteration, followed by a momentum update based on these extrapolations. We demonstrate that the proposed SFOM can accelerate optimization by exploiting the high-order smoothness of the objective function $f$. Assuming that the $p$th-order derivative of $f$ is Lipschitz continuous for some $p\ge2$, and under additional mild assumptions, we establish that our method achieves a sample complexity of $\widetilde{\mathcal{O}}(ε^{-(3p+1)/p})$ for finding a point $x$ such that $\mathbb{E}[\|\nabla f(x)\|]\leε$. To the best of our knowledge, this is the first SFOM to leverage arbitrary-order smoothness of the objective function for acceleration, resulting in a sample complexity that improves upon the best-known results without assuming the mean-squared smoothness condition. Preliminary numerical experiments validate the practical performance of our method and support our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14488
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A stochastic first-order method with multi-extrapolated momentum for highly smooth unconstrained optimization
He, Chuan
Optimization and Control
Artificial Intelligence
Machine Learning
49M05, 49M37, 90C25, 90C30
In this paper, we consider an unconstrained stochastic optimization problem where the objective function exhibits high-order smoothness. Specifically, we propose a new stochastic first-order method (SFOM) with multi-extrapolated momentum, in which multiple extrapolations are performed in each iteration, followed by a momentum update based on these extrapolations. We demonstrate that the proposed SFOM can accelerate optimization by exploiting the high-order smoothness of the objective function $f$. Assuming that the $p$th-order derivative of $f$ is Lipschitz continuous for some $p\ge2$, and under additional mild assumptions, we establish that our method achieves a sample complexity of $\widetilde{\mathcal{O}}(ε^{-(3p+1)/p})$ for finding a point $x$ such that $\mathbb{E}[\|\nabla f(x)\|]\leε$. To the best of our knowledge, this is the first SFOM to leverage arbitrary-order smoothness of the objective function for acceleration, resulting in a sample complexity that improves upon the best-known results without assuming the mean-squared smoothness condition. Preliminary numerical experiments validate the practical performance of our method and support our theoretical findings.
title A stochastic first-order method with multi-extrapolated momentum for highly smooth unconstrained optimization
topic Optimization and Control
Artificial Intelligence
Machine Learning
49M05, 49M37, 90C25, 90C30
url https://arxiv.org/abs/2412.14488