Asymptotically exact inference in differentiable generative models

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


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.
Original languageEnglish
Title of host publicationProceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017
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

Publication series

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


Conference20th International Conference on Artificial Intelligence and Statistics
Abbreviated titleAI-Statistics 2017
Country/TerritoryUnited States
CityFort Lauderdale
Internet address


Dive into the research topics of 'Asymptotically exact inference in differentiable generative models'. Together they form a unique fingerprint.

Cite this