Optimal Analysis of Method with Batching for Monotone Stochastic Finite-Sum Variational Inequalities

TL;DR

This paper introduces an optimal stochastic method for monotone finite-sum variational inequalities that supports batching without sacrificing oracle complexity, validated through experiments.

Contribution

It presents a novel analysis of a batching-supported method achieving optimal convergence for stochastic variational inequalities, unlike previous approaches.

Findings

Supports batching without losing optimal oracle complexity

Achieves optimal convergence estimates for monotone stochastic variational inequalities

Experimental validation confirms effectiveness with small batch sizes

Abstract

Variational inequalities are a universal optimization paradigm that is interesting in itself, but also incorporates classical minimization and saddle point problems. Modern realities encourage to consider stochastic formulations of optimization problems. In this paper, we present an analysis of a method that gives optimal convergence estimates for monotone stochastic finite-sum variational inequalities. In contrast to the previous works, our method supports batching and does not lose the oracle complexity optimality. The effectiveness of the algorithm, especially in the case of small but not single batches is confirmed experimentally.