Asymptotically exact inference in differentiable generative models

DOI10.1214/17-EJS1340SIMaRDI QIDQ1688986zbMATH OpenOpenAlexFDO

Authors Matthew Graham, Amos J. Storkey

Publication date 12 January 2018

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1605.07826, https://projecteuclid.org/euclid.ejs/1513306869

zbMATH Keywords

Markov chain Monte Carloapproximate Bayesian computationimplicit modelsinferencegenerative models

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Bayesian inference (62F15) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40)

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.

Recommendations

• Automatic differentiation variational inference
• Likelihood-free inference via classification
• Deep variational inference
• Towards end‐to‐end likelihood‐free inference with convolutional neural networks
• Bayesian optimization for likelihood-free inference of simulator-based statistical models

Cited in

(12)

• Optimal control for estimation in partially observed elliptic and hypoelliptic linear stochastic differential equations
• A semiparametric generative model for efficient structured-output supervised learning
• Distilling Importance Sampling for Likelihood Free Inference
• Discrepancy-based inference for intractable generative models using quasi-Monte Carlo
• Conditional sampling with monotone GANs: from generative models to likelihood-free inference
• Mining gold from implicit models to improve likelihood-free inference
• Learning variational autoencoders via MCMC speed measures
• Inference and Learning for Generative Capsule Models
• Accelerating inference for stochastic kinetic models
• Quasi-Random Sampling for Multivariate Distributions via Generative Neural Networks
• The frontier of simulation-based inference
• Multilevel Monte Carlo in approximate Bayesian computation

This page was built for publication: Asymptotically exact inference in differentiable generative models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1688986)