Mini-Batch Stochastic Halpern Algorithm for Nonexpansive Fixed point Problems

TL;DR

This paper introduces a mini-batch stochastic version of the Halpern algorithm to efficiently solve large-scale nonexpansive fixed point problems, with proven convergence and rate analysis.

Contribution

It proposes a novel mini-batch stochastic Halpern algorithm with convergence guarantees for large-scale fixed point problems.

Findings

Algorithm converges in mean square to the closest fixed point.

Convergence speed depends on step size settings.

The method addresses computational challenges in large-scale problems.

Abstract

The Halpern algorithm is a powerful fixed point approximation method for finding the closest point in the fixed point set of a nonexpansive mapping to the initial point. However, in practice, it is not necessarily true that this algorithm can be applied to large-scale fixed point problems, since the computation of the nonexpansive mapping is expensive. In this paper, we present mini-batch stochastic Halpern algorithm to resolve the issue caused by the computational difficulty of the mapping. We preform a convergence analysis demonstrating that the algorithm with diminishing step sizes and increasing batch sizes converges in mean square to the closest point in the fixed point set to the initial point. We also perform a convergence rate analysis demonstrating that convergence speed of the algorithm depends on the settings of the diminishing step sizes.