SPARK: Sparse Parametric Antenna Representation using Kernels

2026-01-09

AI Summary

This work addresses the significant overhead in channel state information acquisition and feedback caused by the high-dimensional radiation patterns of massive MIMO and reconfigurable intelligent surfaces (RIS), which hinders efficient beam management. To overcome this, the authors propose a training-free, compressed representation model for radiation patterns. They introduce a novel 3D pattern modeling approach that combines low-order spherical harmonics with anisotropic Gaussian kernels, and for one-dimensional azimuth slices of RIS responses, they design a hybrid sparse representation using Fourier bases and 1D Gaussians. This method yields a hardware-aware, interpretable, and high-fidelity low-dimensional parameterization. Experiments on the AERPAW platform and a public RIS dataset demonstrate reconstruction mean squared errors reduced to 1/2.8 and 1/10.4 of baseline methods, respectively. Simulations further show a 12.65% average uplink throughput gain under a fixed uplink budget.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Channel state information (CSI) acquisition and feedback overhead grows with the number of antennas, users, and reported subbands. This growth becomes a bottleneck for many antenna and reconfigurable intelligent surface (RIS) systems as arrays and user densities scale. Practical CSI feedback and beam management rely on codebooks, where beams are selected via indices rather than explicitly transmitting radiation patterns. Hardware-aware operation requires an explicit representation of the measured antenna/RIS response, yet high-fidelity measured patterns are high-dimensional and costly to handle. We present SPARK (Sparse Parametric Antenna Representation using Kernels), a training-free compression model that decomposes patterns into a smooth global base and sparse localized lobes. For 3D patterns, SPARK uses low-order spherical harmonics for global directivity and anisotropic Gaussian kernels for localized features. For RIS 1D azimuth cuts, it uses a Fourier-series base with 1D Gaussians. On patterns from the AERPAW testbed and a public RIS dataset, SPARK achieves up to 2.8$\times$ and 10.4$\times$ reductions in reconstruction MSE over baselines, respectively. Simulation shows that amortizing a compact pattern description and reporting sparse path descriptors can produce 12.65% mean uplink goodput gain under a fixed uplink budget. Overall, SPARK turns dense patterns into compact, parametric models for scalable, hardware-aware beam management.

Problem

• CSI feedback
• antenna array
• reconfigurable intelligent surface
• beam management
• radiation pattern compression

Innovation

• SPARK
• sparse representation
• parametric modeling
• beam management
• reconfigurable intelligent surface