What type of study is this?

This is a Quantitative Study study.

October 3, 2025Open Access

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

Key Points

PAGE shows improved convergence rates as the parameter τ decreases, enhancing optimization efficiency.
New convergence rates highlight the algorithm's performance in the context of weakly convex finite-sum optimization.
Analysis of PAGE extends its application to a broader class of weakly convex functions, establishing new performance metrics.
The complexity of PAGE decreases with lower values of τ, suggesting enhanced computational efficiency in practical use.

Abstract

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.

Read Full Paperexternally

KI fragen

Bookmark

View Full Paper