Poster (Scientific congresses and symposiums)
Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference
Rozet, François; Louppe, Gilles
2021Fourth Workshop on Machine Learning and the Physical Sciences (NeurIPS 2021)
Peer reviewed
 

Files


Full Text
AMNRE_for_SBI.pdf
Author preprint (1.35 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
simulation-based inference; marginal posterior estimation; likelihood ratio; neural ratio estimation; gravitational waves
Abstract :
[en] In many areas of science, complex phenomena are modeled by stochastic parametric simulators, often featuring high-dimensional parameter spaces and intractable likelihoods. In this context, performing Bayesian inference can be challenging. In this work, we present a novel method that enables amortized inference over arbitrary subsets of the parameters, without resorting to numerical integration, which makes interpretation of the posterior more convenient. Our method is efficient and can be implemented with arbitrary neural network architectures. We demonstrate the applicability of the method on parameter inference of binary black hole systems from gravitational waves observations.
Disciplines :
Space science, astronomy & astrophysics
Computer science
Author, co-author :
Rozet, François  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
Louppe, Gilles  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
Language :
English
Title :
Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference
Publication date :
13 December 2021
Number of pages :
4
Event name :
Fourth Workshop on Machine Learning and the Physical Sciences (NeurIPS 2021)
Event place :
Vancouver, Canada
Event date :
13-12-2021
Audience :
International
Peer reviewed :
Peer reviewed
Available on ORBi :
since 09 November 2021

Statistics


Number of views
68 (20 by ULiège)
Number of downloads
27 (9 by ULiège)

Bibliography


Similar publications



Contact ORBi