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

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.

arXiv comment22 pages, 1 algorithm, 2 figures, 1 table

References in corpus (10)

• Generative Adversarial Networks
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
• A Variational Inequality Perspective on Generative Adversarial Networks
• Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
• Convex Sparse Matrix Factorizations
• SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
• Efficiently Solving MDPs with Stochastic Mirror Descent
• Stochastic Variance Reduction for Variational Inequality Methods
• Lower Complexity Bounds of Finite-Sum Optimization Problems: The Results and Construction