Geometry-Aware Meta-Learning Neural Network for Joint Phase Shift and Precoder Optimization in Reconfigurable Intelligent Surface-Aided Multi-User MISO Systems

A complex-valued, geometry-aware meta-learning neural network that maximizes the weighted sum rate in an RIS-aided multi-user MISO system by leveraging the complex circle geometry for phase shifts and spherical geometry for the precoder, leading to faster convergence and higher weighted sum rates compared to existing approaches.