New First-Order Algorithms for Stochastic Variational Inequalities

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 $\mathcal{O}\left(\frac{{\kappa }^2}{\epsilon }\ln \left(\frac{1}{\epsilon }\right)\right)$

arXiv comment36 pages, 4 figures

References in corpus (6)

• Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML
• Zeroth-Order Algorithms for Nonconvex Minimax Problems with Improved Complexities
• Simple and optimal methods for stochastic variational inequalities, I: operator extrapolation
• Online and Bandit Algorithms for Nonstationary Stochastic Saddle-Point Optimization
• Gradient Free Minimax Optimization: Variance Reduction and Faster Convergence
• A Unifying Framework of Accelerated First-Order Approach to Strongly Monotone Variational Inequalities