Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Cognitive Communications and Networking Année : 2022

Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications

Marios Kountouris
David Gesbert

Résumé

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.
Fichier principal
Vignette du fichier
Robust_Bayesian_Learning.pdf (821.48 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04144056 , version 1 (28-06-2023)

Identifiants

Citer

Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Marios Kountouris, David Gesbert. Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications. IEEE Transactions on Cognitive Communications and Networking, 2022, pp.1-1. ⟨10.1109/TCCN.2023.3261300⟩. ⟨hal-04144056⟩

Collections

EURECOM
26 Consultations
30 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More