Tracking solutions of time-varying variational inequalities

TL;DR

This paper extends the analysis of tracking solutions in time-varying variational inequalities to cases without monotonicity and with periodic variations, exploring convergence and chaotic behaviors through theoretical and experimental studies.

Contribution

It introduces new tracking bounds for non-monotone and periodic time-varying variational inequalities, and analyzes the convergence and chaos in discrete dynamical systems.

Findings

Tracking bounds for non-monotone variational inequalities.

Periodic systems can exhibit chaos or convergence.

Experimental validation of theoretical results.

Abstract

Tracking the solution of time-varying variational inequalities is an important problem with applications in game theory, optimization, and machine learning. Existing work considers time-varying games or time-varying optimization problems. For strongly convex optimization problems or strongly monotone games, these results provide tracking guarantees under the assumption that the variation of the time-varying problem is restrained, that is, problems with a sublinear solution path. In this work we extend existing results in two ways: In our first result, we provide tracking bounds for (1) variational inequalities with a sublinear solution path but not necessarily monotone functions, and (2) for periodic time-varying variational inequalities that do not necessarily have a sublinear solution path-length. Our second main contribution is an extensive study of the convergence behavior and trajectory of discrete dynamical systems of periodic time-varying VI. We show that these systems can exhibit provably chaotic behavior or can converge to the solution. Finally, we illustrate our theoretical results with experiments.