Robust Bayesian Learning for Reliable Wireless AI: Framework and Applications

07/01/2022
by   Matteo Zecchin, et al.
0

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.

READ FULL TEXT
research
08/15/2022

An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models

In this discussion paper, we survey recent research surrounding robustne...
research
05/12/2023

Calibration-Aware Bayesian Learning

Deep learning models, including modern systems like large language model...
research
10/10/2022

Calibrating AI Models for Few-Shot Demodulation via Conformal Prediction

AI tools can be useful to address model deficits in the design of commun...
research
12/15/2022

Calibrating AI Models for Wireless Communications via Conformal Prediction

When used in complex engineered systems, such as communication networks,...
research
05/23/2019

Robust Variational Autoencoder

Machine learning methods often need a large amount of labeled training d...
research
03/17/2023

Operating critical machine learning models in resource constrained regimes

The accelerated development of machine learning methods, primarily deep ...
research
12/02/2022

A Bayesian Framework for Digital Twin-Based Control, Monitoring, and Data Collection in Wireless Systems

Commonly adopted in the manufacturing and aerospace sectors, digital twi...

Please sign up or login with your details

Forgot password? Click here to reset