A PAC-Bayesian Analysis of Channel-Induced Degradation in Edge Inference
This work addresses performance deterioration in edge inference for distributed systems, representing an incremental improvement by adapting existing methods to channel noise.
The paper tackles the mismatch between noiseless training and noisy wireless channels in edge inference by characterizing channel-induced degradation as generalization error, and proposes a channel-aware training algorithm that improves inference accuracy without end-to-end re-training.
In the emerging paradigm of edge inference, neural networks (NNs) are partitioned across distributed edge devices that collaboratively perform inference via wireless transmission. However, standard NNs are generally trained in a noiseless environment, creating a mismatch with the noisy channels during edge deployment. In this paper, we address this issue by characterizing the channel-induced performance deterioration as a generalization error against unseen channels. We introduce an augmented NN model that incorporates channel statistics directly into the weight space, allowing us to derive PAC-Bayesian generalization bounds that explicitly quantifies the impact of wireless distortion. We further provide closed-form expressions for practical channels to demonstrate the tractability of these bounds. Inspired by the theoretical results, we propose a channel-aware training algorithm that minimizes a surrogate objective based on the derived bound. Simulations show that the proposed algorithm can effectively improve inference accuracy by leveraging channel statistics, without end-to-end re-training.