Recent advances in stochastic gradient variational inference have made it
possible to perform variational Bayesian inference with posterior
approximations containing auxiliary random variables. This enables us to
explore a new synthesis of variational inference and Monte Carlo methods where
we incorporate one or more steps of MCMC into our variational approximation. By
doing so we obtain a rich class of inference algorithms bridging the gap
between variational methods and MCMC, and offering the best of both worlds:
fast posterior approximation through the maximization of an explicit objective,
with the option of trading off additional computation for additional accuracy.
We describe the theoretical foundations that make this possible and show some
promising first results.
Description
[1410.6460] Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
%0 Journal Article
%1 salimans2014markov
%A Salimans, Tim
%A Kingma, Diederik P.
%A Welling, Max
%D 2014
%K bayesian
%T Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
%U http://arxiv.org/abs/1410.6460
%X Recent advances in stochastic gradient variational inference have made it
possible to perform variational Bayesian inference with posterior
approximations containing auxiliary random variables. This enables us to
explore a new synthesis of variational inference and Monte Carlo methods where
we incorporate one or more steps of MCMC into our variational approximation. By
doing so we obtain a rich class of inference algorithms bridging the gap
between variational methods and MCMC, and offering the best of both worlds:
fast posterior approximation through the maximization of an explicit objective,
with the option of trading off additional computation for additional accuracy.
We describe the theoretical foundations that make this possible and show some
promising first results.
@article{salimans2014markov,
abstract = {Recent advances in stochastic gradient variational inference have made it
possible to perform variational Bayesian inference with posterior
approximations containing auxiliary random variables. This enables us to
explore a new synthesis of variational inference and Monte Carlo methods where
we incorporate one or more steps of MCMC into our variational approximation. By
doing so we obtain a rich class of inference algorithms bridging the gap
between variational methods and MCMC, and offering the best of both worlds:
fast posterior approximation through the maximization of an explicit objective,
with the option of trading off additional computation for additional accuracy.
We describe the theoretical foundations that make this possible and show some
promising first results.},
added-at = {2019-06-15T01:53:29.000+0200},
author = {Salimans, Tim and Kingma, Diederik P. and Welling, Max},
biburl = {https://www.bibsonomy.org/bibtex/21d906320e35935da61d3013f05da632d/kirk86},
description = {[1410.6460] Markov Chain Monte Carlo and Variational Inference: Bridging the Gap},
interhash = {95bdfcdf1502a29714a9c65c177d086b},
intrahash = {1d906320e35935da61d3013f05da632d},
keywords = {bayesian},
note = {cite arxiv:1410.6460},
timestamp = {2019-06-15T01:53:29.000+0200},
title = {Markov Chain Monte Carlo and Variational Inference: Bridging the Gap},
url = {http://arxiv.org/abs/1410.6460},
year = 2014
}