Method with Batching for Stochastic Finite-Sum Variational Inequalities in Non-Euclidean Setting

Abstract

Variational inequalities are a universal optimization paradigm that incorporate classical minimization and saddle point problems. Nowadays more and more tasks require 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, does not lose the oracle complexity optimality and uses an arbitrary Bregman distance to take into account geometry of the problem. Paper provides experimental confirmation to algorithm's effectiveness.

arXiv comment38 pages, 1 algorithm, 4 figures, 1 table

References in corpus (12)

• Convex Sparse Matrix Factorizations
• Global Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Minimax Problems
• A unified variance-reduced accelerated gradient method for convex optimization
• Stochastic Variance Reduction Methods for Saddle-Point Problems
• Universal gradient descent
• Stochastic Variance Reduction for Variational Inequality Methods
• Lower Complexity Bounds of Finite-Sum Optimization Problems: The Results and Construction
• Optimal Algorithms for Decentralized Stochastic Variational Inequalities
• Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity
• On Accelerated Methods for Saddle-Point Problems with Composite Structure
• Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata
• Bregman Proximal Method for Efficient Communications under Similarity