Abstract
We consider the stochastic generalized Nash equilibrium problem (SGNEP) with joint feasibility constraints and expected-value cost functions. We propose a distributed stochastic projected reflected gradient algorithm and show its almost sure convergence when the pseudogradient mapping is monotone and the solution is unique. The algorithm is based on monotone operator splitting methods tailored for SGNEPs when the expected-value pseudogradient mapping is approximated at each iteration via an increasing number of samples of the random variable. Finally, we show that a preconditioned variant of our proposed algorithm has convergence guarantees when the pseudogradient mapping is cocoercive.
Original language | English |
---|---|
Title of host publication | Proceedings of the 2021 European Control Conference, ECC 2021 |
Publisher | IEEE |
Pages | 369-374 |
ISBN (Electronic) | 978-94-6384-236-5 |
DOIs | |
Publication status | Published - 2021 |
Event | 2021 European Control Conference, ECC 2021 - Delft, Netherlands Duration: 29 Jun 2021 → 2 Jul 2021 |
Conference
Conference | 2021 European Control Conference, ECC 2021 |
---|---|
Country/Territory | Netherlands |
City | Delft |
Period | 29/06/21 → 2/07/21 |