Distributed projected-reflected-gradient algorithms for stochastic generalized Nash equilibrium problems

20 Mar 2020  ·  Barbara Franci, Sergio Grammatico ·

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.

PDF Abstract
No code implementations yet. Submit your code now

Categories


Optimization and Control Computer Science and Game Theory Systems and Control Systems and Control