Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems

DOI10.1109/TSP.2020.3029983MaRDI QIDQ6342485arXivFDO

Authors Olivier Bilenne, Panayotis Mertikopoulos, Elena Veronica Belmega

Publication date 9 June 2020

Published in arXiv

Full work available at URL https://doi.org/10.1109/TSP.2020.3029983

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

arXiv classification

cs.ITeess.SPmath.ITmath.OC

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 iteration$-$a single scalar. In more detail, in a MIMO multiple access channel with $K$ users and $M$ transmit antennas per user, the MXL0${}^{+}$ algorithm achieves $epsilon$-optimality within $extpoly(K,M)/epsilo{n}^2$ 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${}^{+}$ matches$-$and sometimes exceeds$-$that 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.

This page was built for publication: Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6342485)