Edinburgh Research Explorer

Asymptotically exact inference in differentiable generative models

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

Original languageEnglish
Title of host publicationProceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017
PublisherJournal of Machine Learning Research: Workshop and Conference Proceedings
Pages499-508
Number of pages10
Publication statusPublished - 22 Apr 2017
Event20th International Conference on Artificial Intelligence and Statistics - Fort Lauderdale, United States
Duration: 20 Apr 201722 Apr 2017
https://www.aistats.org/aistats2017/

Conference

Conference20th International Conference on Artificial Intelligence and Statistics
Abbreviated titleAI-Statistics 2017
CountryUnited States
CityFort Lauderdale
Period20/04/1722/04/17
Internet address

Abstract

Many generative models can be expressed as a differentiable function of random inputs drawn from some simple probability density. This framework includes both deep generative architectures such as Variational Autoencoders and a large class of procedurally defined simulator models. We present a method for performing efficient MCMC inference in such models when conditioning on observations of the model output. For some models this offers an asymptotically exact inference method where Approximate Bayesian Computation might otherwise be employed. We use the intuition that inference corresponds to integrating a density across the manifold corresponding to the set of inputs consistent with the observed outputs. This motivates the use of a constrained variant of Hamiltonian Monte Carlo which leverages the smooth geometry of the manifold to coherently move between inputs exactly consistent with observations. We validate the method by performing inference tasks in a diverse set of models.

Event

20th International Conference on Artificial Intelligence and Statistics

20/04/1722/04/17

Fort Lauderdale, United States

Event: Conference

Download statistics

No data available

ID: 33200453