New First-Order Algorithms for Stochastic Variational Inequalities

TL;DR

This paper introduces two novel first-order solution schemes for stochastic strongly monotone variational inequalities, achieving optimal iteration complexity and applicable to stochastic minimax problems with noisy data.

Contribution

The paper proposes two new stochastic solution schemes that generalize existing methods and achieve optimal complexity for strongly monotone VI problems.

Findings

Both schemes attain optimal iteration complexity of O(κ log(1/ε)).

Methods can be integrated into zeroth-order approaches for stochastic minimax problems.

The schemes require only one projection per iteration, improving efficiency.

Abstract

In this paper, we propose two new solution schemes to solve the stochastic strongly monotone variational inequality problems: the stochastic extra-point solution scheme and the stochastic extra-momentum solution scheme. The first one is a general scheme based on updating the iterative sequence and an auxiliary extra-point sequence. In the case of deterministic VI model, this approach includes several state-of-the-art first-order methods as its special cases. The second scheme combines two momentum-based directions: the so-called heavy-ball direction and the optimism direction, where only one projection per iteration is required in its updating process. We show that, if the variance of the stochastic oracle is appropriately controlled, then both schemes can be made to achieve optimal iteration complexity of $\mathcal{O}\left(\kappa\ln\left(\frac{1}{\epsilon}\right)\right)$ to reach an $\epsilon$-solution for a strongly monotone VI problem with condition number $\kappa$. We show that these methods can be readily incorporated in a zeroth-order approach to solve stochastic minimax saddle-point problems, where only noisy and biased samples of the objective can be obtained, with a total sample complexity of $\mathcal{O}\left(\frac{\kappa^2}{\epsilon}\ln\left(\frac{1}{\epsilon}\right)\right)$