loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Bogdan Kozyrskiy 1 ; Dimitrios Milios 2 and Maurizio Filippone 1

Affiliations: 1 Department of Data Science, EURECOM, 450 Route des Chappes, Biot, France ; 2 Jubile Tech Ltd., London, U.K.

Keyword(s): Bayesian Inference, Markov Chain Monte-Carlo, Deep Neural Networks.

Abstract: 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 pri or that can be expressed in closed form. We illustrate the effectiveness of our approach with an extensive experimental campaign. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.23.100.174

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kozyrskiy, B., Milios, D. and Filippone, M. (2023). Imposing Functional Priors on Bayesian Neural Networks. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-626-2; ISSN 2184-4313, SciTePress, pages 450-457. DOI: 10.5220/0011742900003411

@conference{icpram23,
author={Bogdan Kozyrskiy and Dimitrios Milios and Maurizio Filippone},
title={Imposing Functional Priors on Bayesian Neural Networks},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2023},
pages={450-457},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011742900003411},
isbn={978-989-758-626-2},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Imposing Functional Priors on Bayesian Neural Networks
SN - 978-989-758-626-2
IS - 2184-4313
AU - Kozyrskiy, B.
AU - Milios, D.
AU - Filippone, M.
PY - 2023
SP - 450
EP - 457
DO - 10.5220/0011742900003411
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic