Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems
Abstract
In this paper, we develop a gradient-free optimization methodology for efficient resource allocation in Gaussian MIMO multiple access channels. Our approach combines two main ingredients: (i) an entropic semidefinite optimization based on matrix exponential learning (MXL); and (ii) a one-shot gradient estimator which achieves low variance through the reuse of past information. This novel algorithm, which we call gradient-free MXL algorithm with callbacks (MXL0), retains the convergence speed of gradient-based methods while requiring minimal feedback per iterationa single scalar. In more detail, in a MIMO multiple access channel with users and transmit antennas per user, the MXL0 algorithm achieves -optimality within iterations (on average and with high probability), even when implemented in a fully distributed, asynchronous manner. For cross-validation, we also perform a series of numerical experiments in medium- to large-scale MIMO networks under realistic channel conditions. Throughout our experiments, the performance of MXL0 matchesand sometimes exceedsthat of gradient-based MXL methods, all the while operating with a vastly reduced communication overhead. In view of these findings, the MXL0 algorithm appears to be uniquely suited for distributed massive MIMO systems where gradient calculations can become prohibitively expensive.
Cite
@article{arxiv.2006.05445,
title = {Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems},
author = {Olivier Bilenne and Panayotis Mertikopoulos and E. Veronica Belmega},
journal= {arXiv preprint arXiv:2006.05445},
year = {2020}
}
Comments
Final version; to appear in IEEE Transactions on Signal Processing; 16 pages, 4 figures