A Gradient Meta-Learning Joint Optimization for Beamforming and Antenna Position in Pinching-Antenna Systems

2025-06-14

AI Summary

This paper addresses the weighted sum-rate (WSR) maximization problem for multi-waveguide coupling antenna systems. Method: We propose a gradient-based meta-learning joint optimization framework that, for the first time, models antenna physical positions as learnable parameters embedded within the meta-learning pipeline. A dual-subnetwork architecture captures local channel tasks, enabling end-to-end joint optimization of beamforming coefficients and antenna positions. The approach integrates convex approximation, equivalent substitution decomposition, and channel-invariant task construction to ensure efficient and stable learning. Contribution/Results: Within 100 iterations, the method achieves a WSR of 5.6 bit/s/Hz—32.7% higher than conventional alternating optimization—while significantly reducing computational complexity and demonstrating strong robustness to initialization.

Technology Category

• Machine Learning: Optimization
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

In this paper, we consider a novel optimization design for multi-waveguide pinching-antenna systems, aiming to maximize the weighted sum rate (WSR) by jointly optimizing beamforming coefficients and antenna position. To handle the formulated non-convex problem, a gradient-based meta-learning joint optimization (GML-JO) algorithm is proposed. Specifically, the original problem is initially decomposed into two sub-problems of beamforming optimization and antenna position optimization through equivalent substitution. Then, the convex approximation methods are used to deal with the nonconvex constraints of sub-problems, and two sub-neural networks are constructed to calculate the sub-problems separately. Different from alternating optimization (AO), where two sub-problems are solved alternately and the solutions are influenced by the initial values, two sub-neural networks of proposed GML-JO with fixed channel coefficients are considered as local sub-tasks and the computation results are used to calculate the loss function of joint optimization. Finally, the parameters of sub-networks are updated using the average loss function over different sub-tasks and the solution that is robust to the initial value is obtained. Simulation results demonstrate that the proposed GML-JO algorithm achieves 5.6 bits/s/Hz WSR within 100 iterations, yielding a 32.7% performance enhancement over conventional AO with substantially reduced computational complexity. Moreover, the proposed GML-JO algorithm is robust to different choices of initialization and yields better performance compared with the existing optimization methods.

Problem

• Jointly optimize beamforming and antenna position
• Maximize weighted sum rate in antenna systems
• Propose gradient-based meta-learning for non-convex optimization

Innovation

• Gradient-based meta-learning joint optimization algorithm
• Decomposed beamforming and antenna position optimization
• Sub-neural networks for robust initial value solutions