Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications

2022-07-01 · Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Marios Kountouris, David Gesbert

This work takes a critical look at the application of conventional machine learning methods to wireless communication problems through the lens of reliability and robustness. Deep learning techniques adopt a frequentist framework, and are known to provide poorly calibrated decisions that do not reproduce the true uncertainty caused by limitations in the size of the training data. Bayesian learning, while in principle capable of addressing this shortcoming, is in practice impaired by model misspecification and by the presence of outliers. Both problems are pervasive in wireless communication settings, in which the capacity of machine learning models is subject to resource constraints and training data is affected by noise and interference. In this context, we explore the application of the framework of robust Bayesian learning. After a tutorial-style introduction to robust Bayesian learning, we showcase the merits of robust Bayesian learning on several important wireless communication problems in terms of accuracy, calibration, and robustness to outliers and misspecification.

📄 PDF Abstract BibTeX arXiv:2207.00300

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity

2025-06-06 · Jun-Pyo Hong, Hyowoon Seo, Kisong Lee

The conventional FL methods face critical challenges in realistic wireless edge networks, where training data is both limited and heterogeneous, often leading to unstable training and poor generalization. To address thes…

Bayesian Inference Federated Learning

Prediction of Rare Channel Conditions using Bayesian Statistics and Extreme Value Theory

2024-07-01 · Tobias Kallehauge, Anders E. Kalør, Pablo Ramírez-Espinosa, Christophe Biscio 외

Estimating the probability of rare channel conditions is a central challenge in ultra-reliable wireless communication, where random events, such as deep fades, can cause sudden variations in the channel quality. This pap…

Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design

2025-08-03 · Xiangwang Hou, Jingjing Wang, Fangming Guan, Jun Du 외 arxiv

Emerging real-time computer vision (CV) applications on wireless edge devices demand energy-efficient and privacy-preserving learning. Federated learning (FL) enables on-device training without raw data sharing, yet rema…

Federated Learning Data Augmentation

Design of a Highly Reliable Wireless Module for Ultra-Low-Latency Short Range Applications

2018-11-29

Current radio systems are currently optimized for capacity and range. However, certain applications of wireless systems require fast and reliable communication over short distances. The challenge of these systems is to c…

Reliability Modeling, Analysis and Prediction of Wireless Mobile Communications