Annealed Langevin Dynamics for Massive MIMO Detection
Jun 1, 2022·,
,,·
0 min read
Nicolas Zilberstein
Chris Dick
Rahman Doost-Mohammady
Ashutosh Sabharwal
Santiago Segarra
Abstract
Optimal symbol detection in massive MIMO systems is NP-hard, motivating
approximate methods that trade complexity for performance. We propose a
detector based on annealed Langevin dynamics, which samples from a
carefully designed energy landscape to recover transmitted symbols. The
approach yields near-ML detection accuracy at substantially lower
complexity than traditional sphere-decoding-based methods, and remains
effective at large array sizes and high modulation orders.
Type
Publication
IEEE Transactions on Wireless Communications, 22(6)
Authors
Authors
Authors
Rahman Doost-Mohammady
(he/him)
Assistant Research Professor
I work at the intersection of computer systems and wireless
networking — building programmable, intelligent infrastructure for
5G/6G and Open RAN. A common thread across my projects is algorithm
and system design across FPGA, GPU, and CPU — spanning real-time
massive MIMO baseband on commodity servers, many-antenna hardware
platforms, and learning-driven schedulers. I am currently focused on
virtualized Open RAN systems and ML-enabled RAN software design.
Authors
Authors