MIMO Channel Prediction via Deep Learning-based Conformal Bayes Filter

TL;DR

This paper introduces a deep learning-based conformal Bayes filter for MIMO channel prediction, effectively combining DL, conformal quantile regression, and Bayesian filtering to improve accuracy and uncertainty calibration over traditional methods.

Contribution

It presents a novel DCBF framework that enhances DL-based channel prediction by integrating uncertainty calibration and Bayesian filtering, addressing limitations of existing approaches.

Findings

DCBF significantly improves channel prediction accuracy.

Outperforms traditional Kalman filter-based methods.

Provides reliable uncertainty estimates for predictions.

Abstract

Channel prediction has emerged as an effective solution for acquiring accurate channel state information (CSI) in the presense of channel aging. Existing methods have inherent limitations, with conventional Kalman filter (KF)-based approach being vulnerable to model mismatch and deep learning (DL)-based approaches producing overconfident predictions. To address these issues, we propose a DL-based conformal Bayes filter (DCBF) that integrates DL-based prediction, conformal quantile regression (CQR), and Bayesian filtering. The proposed framework enables principled fusion of calibrated priors and observations, yielding reliable channel predictions with the calibrated uncertainty. Simulation results demonstrate that DCBF significantly improves DL-based prediction and outperforms the KF-based method.