Self-Tuned Stochastic Approximation Schemes for Non-Lipschitzian Stochastic Multi-User Optimization and Nash Games

Farzad Yousefian, Angelia Nedić, Uday V. Shanbhag

Research output: Contribution to journalArticlepeer-review

36 Scopus citations

Abstract

We consider multi-user optimization problems and Nash games with stochastic convex objectives, instances of which arise in decentralized control problems. The associated equilibrium conditions of both problems can be cast as Cartesian stochastic variational inequality problems with mappings that are strongly monotone but not necessarily Lipschitz continuous. Consequently, most of the currently available stochastic approximation schemes cannot address such problems. First, through a user-specific local smoothing, we derive an approximate map that is shown to be Lipschitz continuous with a prescribed constant. Second, motivated by the need for a robust scheme that can be implemented in a distributed fashion, we develop a distributed self-tuned stochastic approximation scheme (DSSA) that adapts to problem parameters. Importantly, this scheme is provably convergent in an almost-sure sense and displays the optimal rate of convergence in mean squared error, i.e., O(1/k). A locally randomized variant is also provided to ensure that the scheme can contend with stochastic non-Lipschitzian multi-user problems. We conclude with numerics derived from a stochastic Nash-Cournot game.

Original languageEnglish (US)
Article number7258341
Pages (from-to)1753-1766
Number of pages14
JournalIEEE Transactions on Automatic Control
Volume61
Issue number7
DOIs
StatePublished - Jul 2016
Externally publishedYes

Keywords

  • Self-tuned stepsizes
  • stochastic Nash games
  • stochastic approximation methods
  • stochastic multi-agent optimization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Self-Tuned Stochastic Approximation Schemes for Non-Lipschitzian Stochastic Multi-User Optimization and Nash Games'. Together they form a unique fingerprint.

Cite this