Bayesian optimization for adaptive MCMC

Bayesian optimization for adaptive MCMC

Show other versions (2)

A new randomized strategy for adaptive Markov chain Monte Carlo (MCMC) using Bayesian optimization, called Bayesian-optimized MCMC, is proposed. This approach can handle non-differentiable objective functions and trades off exploration and exploitation to reduce the number of function evaluations. B...

Full description

Bibliographic Details
Main Author: Mahendran, Nimalan
Language:English
Published: University of British Columbia 2011
Online Access:http://hdl.handle.net/2429/30636
id ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.2429-30636
record_format oai_dc
spelling ndltd-LACETR-oai-collectionscanada.gc.ca-BVAU.2429-306362014-03-26T03:37:28Z Bayesian optimization for adaptive MCMC Mahendran, Nimalan A new randomized strategy for adaptive Markov chain Monte Carlo (MCMC) using Bayesian optimization, called Bayesian-optimized MCMC, is proposed. This approach can handle non-differentiable objective functions and trades off exploration and exploitation to reduce the number of function evaluations. Bayesian-optimized MCMC is applied to the complex setting of sampling from constrained, discrete and densely connected probabilistic graphical models where, for each variation of the problem, one needs to adjust the parameters of the proposal mechanism automatically to ensure efficient mixing of the Markov chains. It is found that Bayesian-optimized MCMC is able to match or surpass manual tuning of the proposal mechanism by a domain expert. 2011-01-14T22:03:17Z 2011-01-14T22:03:17Z 2011 2011-01-14T22:03:17Z 2011-05 Electronic Thesis or Dissertation http://hdl.handle.net/2429/30636 eng University of British Columbia
collection NDLTD
language English
sources NDLTD
description A new randomized strategy for adaptive Markov chain Monte Carlo (MCMC) using Bayesian optimization, called Bayesian-optimized MCMC, is proposed. This approach can handle non-differentiable objective functions and trades off exploration and exploitation to reduce the number of function evaluations. Bayesian-optimized MCMC is applied to the complex setting of sampling from constrained, discrete and densely connected probabilistic graphical models where, for each variation of the problem, one needs to adjust the parameters of the proposal mechanism automatically to ensure efficient mixing of the Markov chains. It is found that Bayesian-optimized MCMC is able to match or surpass manual tuning of the proposal mechanism by a domain expert.
author Mahendran, Nimalan
spellingShingle Mahendran, Nimalan
Bayesian optimization for adaptive MCMC
author_facet Mahendran, Nimalan
author_sort Mahendran, Nimalan
title Bayesian optimization for adaptive MCMC
title_short Bayesian optimization for adaptive MCMC
title_full Bayesian optimization for adaptive MCMC
title_fullStr Bayesian optimization for adaptive MCMC
title_full_unstemmed Bayesian optimization for adaptive MCMC
title_sort bayesian optimization for adaptive mcmc
publisher University of British Columbia
publishDate 2011
url http://hdl.handle.net/2429/30636
work_keys_str_mv AT mahendrannimalan bayesianoptimizationforadaptivemcmc
_version_ 1716655845777866752

Similar Items