Stochastic mirror descent dynamics and their convergence in monotone variational inequalities

Panayotis Mertikopoulos, Mathias Staudigl

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

We examine a class of stochastic mirror descent dynamics in the context of monotone variational inequalities (including Nash equilibrium and saddle-point problems). The dynamics under study are formulated as a stochastic differential equation, driven by a (single-valued) monotone operator and perturbed by a Brownian motion. The system's controllable parameters are two variable weight sequences, that, respectively, pre- and post-multiply the driver of the process. By carefully tuning these parameters, we obtain global convergence in the ergodic sense, and we estimate the average rate of convergence of the process. We also establish a large deviations principle, showing that individual trajectories exhibit exponential concentration around this average.

Original languageEnglish
Pages (from-to)838-867
Number of pages30
JournalJournal of Optimization Theory and Applications
Volume179
Issue number3
DOIs
Publication statusPublished - Dec 2018

Keywords

  • Mirror descent
  • Variational inequalities
  • Saddle-point problems
  • Stochastic differential equations
  • 90C25
  • 90C33
  • 90C47
  • LONG-TIME BEHAVIOR
  • OPERATORS
  • SYSTEMS
  • ALGORITHMS
  • EQUATIONS
  • FLOWS

Cite this