Variational Noise-Contrastive Estimation

Ben Rhodes, Michael Gutmann

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

Abstract

Unnormalised latent variable models are a broad and flexible class of statistical models. However, learning their parameters from data is intractable, and few estimation techniques are currently available for such models. To increase the number of techniques in our arsenal, we propose variational noisecontrastive estimation (VNCE), building on NCE which is a method that only applies to unnormalised models. The core idea is to use a variational lower bound to the NCE objective function, which can be optimised in the same fashion as the evidence lower bound (ELBO) in standard variational inference (VI). We prove that VNCE can be used for both parameter estimation of unnormalised models and posterior inference of latent variables. The developed theory shows that VNCE has the same level of generality as standard VI, meaning that advances made there can be directly imported to the unnormalised setting. We validate VNCE on toy models and apply it to a realistic problem of estimating an undirected graphical model from incomplete data.
Original languageEnglish
Title of host publicationProceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)
Place of PublicationNaha, Okinawa, Japan
PublisherPMLR
Pages2741-2750
Number of pages14
Volume89
Publication statusPublished - 25 Apr 2019
Event22nd International Conference on Artificial Intelligence and Statistics - Naha, Japan
Duration: 16 Apr 201918 Apr 2019
https://www.aistats.org/

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume89
ISSN (Electronic)2640-3498

Conference

Conference22nd International Conference on Artificial Intelligence and Statistics
Abbreviated titleAISTATS 2019
Country/TerritoryJapan
CityNaha
Period16/04/1918/04/19
Internet address

Fingerprint

Dive into the research topics of 'Variational Noise-Contrastive Estimation'. Together they form a unique fingerprint.

Cite this