A Particle-Swarm-Assisted Gradient Meta-Learning Algorithm for Joint Transmit Precoding and STAR-RIS Coefficient Optimization

This paper proposes a particle‑swarm‑assisted gradient meta‑learning (PSA‑GML) algorithm to jointly optimize the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR‑RIS) for maximizing weighted sum rate in a multi‑user downlink. The method first transforms the non‑convex problem via amplitude‑split parameterization and collapsed precoder representation, then uses particle swarm optimization to generate a robust warm start for the STAR‑RIS coefficients, and finally refines both coefficients and precoder with a coordinate‑wise LSTM meta‑optimizer trained by first‑order gradient meta‑learning. Numerical results demonstrate that PSA‑GML achieves an 11.06 bits/s/Hz weighted sum rate at 10 dB, outperforming conventional alternating optimization by 13.1 % and the random‑phase scheme by 35.1 %, while also showing strong zero‑shot transfer across regimes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.