AI-Aided Annealed Langevin Dynamics for Rapid Optimization of Programmable Channels

• Published in: SPAWC : signal processing advances in wireless communications pp. 1 - 5
• Main Authors: Shaked, Tomer, Del Hougne, Philipp, Alexandropoulos, George C., Shlezinger, Nir
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07.07.2025
• Subjects: Active learning; Annealing; Artificial neural networks; Diffusion; Heuristic algorithms; intelligent surfaces; Numerical models; Optimization; Signal processing algorithms; Training; Tuning; Wireless communication
• ISSN: 1948-3252
• DOI: 10.1109/SPAWC66079.2025.11143453

Emerging technologies such as reconfigurable intelligent surfaces (RISs) make it possible to optimize some parameters of wireless channels. Conventional approaches require relating the channel and its programmable parameters via a simple model that supports rapid optimization, e.g., re-tuning the parameters each time the users move. However, in practice such models are often crude approximations of the channel, and a more faithful description can be obtained via complex simulators, or only by measurements. In this work, we introduce a novel approach for rapid optimization of programmable channels based on AI -aided annealed Langevin dynamics (ALD), which bypasses the need for explicit channel modeling. By framing the ALD algorithm using the maximum a-posteriori probability (MAP) estimate, we design a deep unfolded ALD algorithm that leverages a deep neural network (DNN) to estimate score gradients for optimizing channel parameters. We introduce a training method that overcomes the need for channel modeling using zero-order gradients, combined with active learning to enhance generalization, enabling optimization in complex and dynamically changing environments. We evaluate the proposed method in RIS-aided scenarios subject to rich-scattering effects. Our results demonstrate that our AI -aided ALD method enables rapid and reliable channel parameter tuning with limited latency.