Online Learning of Modular Bayesian Deep Receivers: Single-Step Adaptation with Streaming Data

TL;DR

This paper introduces a single-step Bayesian online learning method for modular DNN-based wireless receivers, enabling rapid adaptation to changing channels with low latency and improved robustness over traditional gradient-based approaches.

Contribution

It presents a novel Bayesian tracking framework for online DNN adaptation, allowing single-step updates and modular architectures for efficient wireless receiver training.

Findings

Maintains low error rates in dynamic channels

Reduces update latency significantly

Enhances robustness to channel variability

Abstract

Deep neural network (DNN)-based receivers offer a powerful alternative to classical model-based designs for wireless communication, especially in complex and nonlinear propagation environments. However, their adoption is challenged by the rapid variability of wireless channels, which makes pre-trained static DNN-based receivers ineffective, and by the latency and computational burden of online stochastic gradient descent (SGD)-based learning. In this work, we propose an online learning framework that enables rapid low-complexity adaptation of DNN-based receivers. Our approach is based on two main tenets. First, we cast online learning as Bayesian tracking in parameter space, enabling a single-step adaptation, which deviates from multi-epoch SGD . Second, we focus on modular DNN architectures that enable parallel, online, and localized variational Bayesian updates. Simulations with practical communication channels demonstrate that our proposed online learning framework can maintain a low error rate with markedly reduced update latency and increased robustness to channel dynamics as compared to traditional gradient descent based method.