Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity

Abstract

Two of the most prominent algorithms for solving unconstrained smooth games are the classical stochastic gradient descent-ascent (SGDA) and the recently introduced stochastic consensus optimization (SCO) [Mescheder et al., 2017]. SGDA is known to converge to a stationary point for specific classes of games, but current convergence analyses require a bounded variance assumption. SCO is used successfully for solving large-scale adversarial problems, but its convergence guarantees are limited to its deterministic variant. In this work, we introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO under this condition for solving a class of stochastic variational inequality problems that are potentially non-monotone. We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size, and we propose insightful stepsize-switching rules to guarantee convergence to the exact solution. In addition, our convergence guarantees hold under the arbitrary sampling paradigm, and as such, we give insights into the complexity of minibatching.

35th Conference on Neural Information Processing Systems (NeurIPS 2021)

References in corpus (6)

• Connecting Generative Adversarial Networks and Actor-Critic Methods
• Global Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Minimax Problems
• A Stochastic forward-backward splitting method for solving monotone inclusions in Hilbert spaces
• Stochastic Hamiltonian Gradient Methods for Smooth Games
• Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities
• Stochastic Gradient Descent on Nonconvex Functions with General Noise Models