On Contrastive Learning for Likelihood-free Inference

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Likelihood-free methods perform parameter inference in stochastic simulator models where evaluating the likelihood is intractable but sampling synthetic data is possible. One class of methods for this likelihood-free problem uses a classifier to distinguish between pairs of parameter-observation samples generated using the simulator and pairs sampled from some reference distribution, which implicitly learns a density ratio proportional to the likelihood. Another popular class of methods fits a conditional distribution to the parameter posterior directly, and a particular recent variant allows for the use of flexible neural density estimators for this task. In this work, we show that both of these approaches can be unified under a general contrastive learning scheme, and clarify how they should be run and compared.
Original languageEnglish
Title of host publicationProceedings of the 37th International Conference on Machine Learning
PublisherPMLR
Pages2771-2781
Number of pages15
Publication statusPublished - 18 Jul 2020
EventThirty-seventh International Conference on Machine Learning 2020 - Virtual conference
Duration: 13 Jul 202018 Jul 2020
https://icml.cc/

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume119
ISSN (Electronic)2640-3498

Conference

ConferenceThirty-seventh International Conference on Machine Learning 2020
Abbreviated titleICML 2020
CityVirtual conference
Period13/07/2018/07/20
Internet address

Fingerprint Dive into the research topics of 'On Contrastive Learning for Likelihood-free Inference'. Together they form a unique fingerprint.

Cite this