Distributed stochastic optimization via matrix exponential learning
This addresses the problem of optimizing energy efficiency in distributed wireless networks, offering a robust solution under high uncertainty, though it is incremental as it builds on existing matrix exponential learning methods.
The paper tackles distributed stochastic optimization in signal processing and wireless communications by proposing a matrix exponential learning algorithm that converges to stable Nash equilibria, achieving a 100% to 500% increase in energy efficiency for users in multi-carrier/multiple-antenna scenarios.
In this paper, we investigate a distributed learning scheme for a broad class of stochastic optimization problems and games that arise in signal processing and wireless communications. The proposed algorithm relies on the method of matrix exponential learning (MXL) and only requires locally computable gradient observations that are possibly imperfect and/or obsolete. To analyze it, we introduce the notion of a stable Nash equilibrium and we show that the algorithm is globally convergent to such equilibria - or locally convergent when an equilibrium is only locally stable. We also derive an explicit linear bound for the algorithm's convergence speed, which remains valid under measurement errors and uncertainty of arbitrarily high variance. To validate our theoretical analysis, we test the algorithm in realistic multi-carrier/multiple-antenna wireless scenarios where several users seek to maximize their energy efficiency. Our results show that learning allows users to attain a net increase between 100% and 500% in energy efficiency, even under very high uncertainty.