Imposing functional priors on Bayesian neural networks

Kozyrskiy, Bogdan; Milios, Dimitrios; Filippone, Maurizio
ICPRAM 2023, 12th International Conference on Pattern Recognition Applications and Methods, 22-24 February 2023, Lisbon, Portugal

Specifying sensible priors for Bayesian neural networks (BNNs) is key to obtain state-of-the-art predictive performance while obtaining sound predictive uncertainties. However, this is generally difficult because of the complex way prior distributions induce distributions over the functions that BNNs can represent. Switching the focus from the prior over the weights to such functional priors allows for the reasoning on what meaningful prior information should be incorporated. We propose to enforce such meaningful functional priors through Gaussian processes (GPs), which we view as a form of implicit prior over the weights, and we employ scalable Markov chain Monte Carlo (MCMC) to obtain samples from an approximation to the posterior distribution over BNN weights. Unlike previous approaches, our proposal does not require the modification of the original BNN model, it does not require any expensive preliminary optimization, and it can use any inference techniques and any functional prior that can be expressed in closed form. We illustrate the effectiveness of our approach with an extensive experimental campaign. 

Data Science
Eurecom Ref:
© 2023 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.