Go to  Advanced Search

Predictive adaptation of hybrid Monte Carlo with bandits

Show full item record

Files in this item

Files Size Format Description   View
ubc_2012_fall_wang_ziyu.pdf 1.116Mb Adobe Portable Document Format   View/Open
Title: Predictive adaptation of hybrid Monte Carlo with bandits
Author: Wang, Ziyu
Degree Master of Science - MSc
Program Computer Science
Copyright Date: 2012
Publicly Available in cIRcle 2012-10-10
Abstract: This thesis introduces a novel way of adapting the Hybrid Monte Carlo (HMC) algorithm using Gaussian process bandits. HMC is a powerful Markov chain Monte Carlo (MCMC) method, but it requires careful tuning of its hyper-parameters. We propose a Gaussian process bandit approach to carry out the adaptation of the hyper-parameters while the Markov chain progresses. We also introduce the use of cross-validation error measures for adaptation, which we believe are more pragmatic than many existing adaptation objectives. The new measures take the intended statistical use of the model, whose parameters are estimated by HMC, into consideration. We apply these two innovations to the adaptation of HMC for prediction and feature selection with multi-layer feed-forward neural networks. The experiments with synthetic and real data show that the proposed adaptive scheme is not only automatic, but also does better tuning than human experts.
URI: http://hdl.handle.net/2429/43362
Scholarly Level: Graduate

This item appears in the following Collection(s)

Show full item record

All items in cIRcle are protected by copyright, with all rights reserved.

UBC Library
1961 East Mall
Vancouver, B.C.
Canada V6T 1Z1
Tel: 604-822-6375
Fax: 604-822-3893