Stochastic mirror descent dynamics and their convergence in monotone variational inequalities - Archive ouverte HAL Access content directly
Journal Articles Journal of Optimization Theory and Applications Year : 2018

Stochastic mirror descent dynamics and their convergence in monotone variational inequalities

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 sto- chastic 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.
Fichier principal
Vignette du fichier
MonotoneSMD.pdf (571.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01643343 , version 1 (09-10-2018)

Identifiers

Cite

Panayotis Mertikopoulos, Mathias Staudigl. Stochastic mirror descent dynamics and their convergence in monotone variational inequalities. Journal of Optimization Theory and Applications, In press, 179 (3), pp.838-867. ⟨10.1007/s10957-018-1346-x⟩. ⟨hal-01643343⟩
162 View
138 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More