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.
This paper investigates the joint optimization of the transmit precoder and the transmission/reflection coefficients of a simultaneously transmitting and reflecting reconfigurable intelligent surface...
arXiv:2606. 00862v1 Announce Type: cross Abstract: Surrogate-assisted evolutionary algorithms (SAEAs) have been widely used for expensive black-box optimization problems.
Learned optimization aims to improve upon hand-designed optimizers (e. g.
arXiv:2609.00284v1 Announce Type: cross Abstract: Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traff...
arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.
arXiv:2607. 00860v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) beam alignment plays a critical role in next-generation wireless systems, yet its efficient implementation remains challenging.
arXiv:2606. 31334v1 Announce Type: new Abstract: Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min fairness, and peak-to-average power ratio (PAPR)-constrained objectives.
arXiv:2603. 18853v3 Announce Type: replace-cross Abstract: Autonomous aerial vehicles (AAVs) enable data collection for sixth-generation Internet-of-Things networks, but their trajectories couple nonlinear wireless rates with long-horizon service progress.
arXiv:2607. 19331v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is rapidly advancing the reasoning capabilities of language models, yet the optimization layer that converts reward feedback into weight-space updates remains poorly understood.
Agentic ESOpt proposes using evolution strategies (ES) instead of reinforcement learning to fine‑tune large language‑model agents for long‑horizon tasks. ES offers model scalability, flexibility, and better long‑horizon credit assignment, enabling full‑parameter optimization with minimal GPU memory. The framework samples parameter perturbations, evaluates agents with rewards, and updates online, achieving notable performance gains on WebArena‑Lite and in test‑time prompt‑parameter co‑evolution.
PRIME is a plug‑in residual input‑conditioned mixture of experts that preserves the original dense prediction path while adding low‑rank, input‑dependent logit corrections. By initializing residuals to zero, PRIME matches the baseline dense model at training start and stabilizes conditional estimation with multi‑bag aggregation and EMA load biases. Experiments on Avazu and Criteo across 13 CTR architectures show modest AUC and LogLoss gains, with PRIME outperforming APG on FiBiNET and DCNv2 while using fewer parameters and lower latency.
arXiv:2608. 01997v1 Announce Type: new Abstract: Single-optimizer training is a poor fit for the distinct phases of deep network optimization: adaptive methods handle noisy early gradients well but overshoot flat minima, while SGD with momentum generalizes better in the late phase but converges slowly early on.