扩散模型用于 MIMO 信道估计:α-stable 先验优于高斯先验
Temporal Diffusion Models for Joint Signal-Channel Estimation under Gaussian and $α$-Stable MIMO Channels
做通信信号处理的值得看看这篇:他们把扩散模型用在 MIMO 信道估计上,发现重尾噪声下用 α-stable 先验比高斯先验效果好,还不用重新训练就能换分布。搞 6G 或智能信道估计的研究者可以参考这套似然引导方法。
一篇 arXiv 论文提出用扩散模型在 MIMO 系统中做信号与信道的联合估计,覆盖高斯与对称 α-stable 两类衰落信道。方法分两个场景:仅基于导频的信道估计,以及图像与信道的盲联合恢复,后者用独立的扩散模型分别建模图像和信道,再通过观测似然引导反向扩散过程来组合两者的估计。
技术上,作者用似然引导(likelihood guidance)细化标准扩散与 score-based 模型,并证明同一个训练好的扩散模型可以直接复用于 location-scale 分布族而无需重新训练。论文还引入时序重建(temporal reconstruction),利用先前观测信息改进估计,在时变信道模型下同时提升信道估计精度与重建图像质量。
实验结论是:对同一重尾信道数据,α-stable 扩散先验的信道估计和图像重建效果都优于高斯扩散先验。这提示通信信号处理领域,扩散先验的选择应匹配信道噪声的实际分布特性。
Temporal Diffusion Models for Joint Signal-Channel Estimation under Gaussian and $α$-Stable MIMO Channels
Diffusion models have emerged as powerful tools for learning complex data distributions and solving inverse problems. However, most diffusion models rely on the Gaussian distribution, which does not accurately represent heavy-tailed data. In this work, we study diffusion-based reconstruction under Gaussian and symmetric $α$-stable fading channels, while also exploring the benefits of using possible temporal dependence in the channel. We consider two variants: pilot-based channel-only estimation and joint image-channel recovery for MIMO systems. Our approach is based on several standard and score-based diffusion models for both Gaussian and $α$-stable distributions. We refine these models by guiding the reverse diffusion process using the observation likelihood and show how a single trained diffusion model can be reused for the location-scale family of distributions without retraining. In blind MIMO recovery, separate diffusion models are used for the image and channel, and their estimates are combined through likelihood guidance. For each setting, we compare independent and temporal reconstruction, where information from previous observations is used to improve the estimation. We show that, under a time-dependent channel model, such a temporal reconstruction improves channel estimation and the quality of the reconstructed image. Finally, we show that, for the same heavy-tailed channel data, using an $α$-stable diffusion prior provides better channel estimation and image reconstruction than using a Gaussian diffusion prior.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include diffusion models, MIMO, channel estimation.
Source attribution: curated from arXiv cs.LG (@Rawad Kansoh, Bahaa Ammoury, Charbel Hannoun, Jihad Fahs, Ibrahim Abou-Faycal).