Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Condat, Laurent, Richtárik, Peter
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918144706084864
author Condat, Laurent
Richtárik, Peter
author_facet Condat, Laurent
Richtárik, Peter
contents PAGE, a stochastic algorithm introduced by Li et al. [2021], was designed to find stationary points of averages of smooth nonconvex functions. In this work, we study PAGE in the broad framework of $τ$-weakly convex functions, which provides a continuous interpolation between the general nonconvex $L$-smooth case ($τ= L$) and the convex case ($τ= 0$). We establish new convergence rates for PAGE, showing that its complexity improves as $τ$ decreases.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00737
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization
Condat, Laurent
Richtárik, Peter
Optimization and Control
Machine Learning
PAGE, a stochastic algorithm introduced by Li et al. [2021], was designed to find stationary points of averages of smooth nonconvex functions. In this work, we study PAGE in the broad framework of $τ$-weakly convex functions, which provides a continuous interpolation between the general nonconvex $L$-smooth case ($τ= L$) and the convex case ($τ= 0$). We establish new convergence rates for PAGE, showing that its complexity improves as $τ$ decreases.
title Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2509.00737