arXiv AI

GCNO: Gramian Chebyshev Neural Operator for Physics-Based Compression of Wireless Channels

The paper introduces GCNO, a physics‑based, variable‑rate neural operator that compresses wireless channel matrices by identifying a sample‑dependent set of dominant propagation paths instead of treating the matrix as an image. GCNO leverages receive‑transmit channel structure, a first‑order Taylor correction, and least‑squares recovery to encode path directions and strengths, and the base station reconstructs the channel analytically from these tuples. Experiments on three ray‑traced environments show GCNO outperforms neural feedback baselines in reconstruction accuracy for the same payload or achieves the same accuracy with lower payload, and it generalizes to unseen antenna counts without retraining.

Hugging Face Trending Papers
3d ago

GCNO: Gramian Chebyshev Neural Operator for Physics-Based Compression of Wireless Channels

GCNO: Gramian Chebyshev Neural Operator for Physics-Based Compression of Wireless Channels proposes a variable‑rate compressor that reports only the dominant propagation paths of a wireless channel instead of a full complex‑valued matrix. The method uses the channel’s receive‑transmit structure to locate paths, applies a first‑order Taylor correction for sub‑grid directions, and recovers path strengths via least squares, all trained without explicit path labels. Experiments on three ray‑traced environments show GCNO outperforms neural feedback baselines in reconstruction accuracy for the same payload or achieves the same accuracy with a lower payload, and it generalizes to unseen antenna counts without retraining.

arXiv AI
2d ago

Physics-Unrolled Neural Operator for Wireless Field Modeling

The paper introduces Physics-Unrolled Hybrid Neural Operator (PU‑HNO), a three‑stage cascade that transforms low‑fidelity ray‑tracing outputs and scene priors into high‑fidelity indoor radio maps by sequentially modeling reflection, diffraction, and scattering. It demonstrates that, under conditionally unbiased label noise, the model can learn stable propagation structures and surpass its own training labels. Experiments on varied floorplans show PU‑HNO outperforming image‑to‑image baselines, wireless learning models, and monolithic neural operators in both image quality and wireless deployment metrics.

By Rafid Umayer Murshed, Saif Ur Rahman, Mingyue Tang, Elahe Soltanaghai
arXiv AI
Jul 8

Contrastive Predictive Coding with Compression for Enhanced Channel State Feedback in Wireless Networks

arXiv:2607. 05419v1 Announce Type: cross Abstract: Accurate and timely channel state information (CSI) is essential for next-generation wireless systems, yet existing works treat CSI compression and CSI prediction as separate problems, both in academia and in current 3GPP studies.

By Ahmed Y. Radwan, Hina Tabassum, Fahad Syed Muhammad, Matthew Baker
Hugging Face Trending Papers
Aug 5

MultiPathFormer: Towards a Foundation Model for Multipath Wireless Propagation

Recent advances in machine learning have enabled training of wireless foundation models, which aim to support tasks such as channel estimation, beam prediction, and localization based on wireless signals. Existing wireless foundation models typically pretrain on channel tensors using masked reconstruction over subcarriers, antennas, or time but ignore the physical characteristics of wireless propagation.

arXiv Machine Learning
Jun 16

Context-Aware Markov VAE for CSI Compression in Wireless Systems

arXiv:2606. 16607v1 Announce Type: cross Abstract: This paper considers neural channel state information (CSI) compression for time-varying massive multiple-input multiple-output (MIMO) channels in frequency division duplex (FDD) systems with limited feedback resources.

By Efstathios Chatziloizos, Konstantinos Vandikas, Aneta Vulgarakis Feljan, Zheng Chen, Nikolaos Pappas