Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Fast Gradient-Free Optimization 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) the entropic semidefinite optimization method of matrix exponential learning (MXL); and (ii) a one-shot gradient estimator which achieves low variance through the reuse of past information. Owing to this reuse mechanism, the proposed 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 ε-optimality within poly(K,M)/ε² 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.
Complete list of metadatas

Cited literature [34 references]  Display  Hide  Download
Contributor : Olivier Bilenne <>
Submitted on : Tuesday, June 9, 2020 - 8:23:58 AM
Last modification on : Friday, July 17, 2020 - 11:12:03 AM


Files produced by the author(s)


  • HAL Id : hal-02861460, version 1


Olivier Bilenne, Panayotis Mertikopoulos, Elena Veronica Belmega. Fast Gradient-Free Optimization in Distributed Multi-User MIMO Systems. 2020. ⟨hal-02861460⟩



Record views


Files downloads