{"ID":2844664,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06045","arxiv_id":"2511.06045","title":"Online Learning of Modular Bayesian Deep Receivers: Single-Step Adaptation with Streaming Data","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.","short_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...","url_abs":"https://arxiv.org/abs/2511.06045","url_pdf":"https://arxiv.org/pdf/2511.06045v2","authors":"[\"Yakov Gusakov\",\"Osvaldo Simeone\",\"Tirza Routtenberg\",\"Nir Shlezinger\"]","published":"2025-11-08T15:34:34Z","proceeding":"eess.SP","tasks":"[\"eess.SP\",\"cs.IT\"]","methods":"[]","has_code":false}