Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior

Thumbnail Image
Download
Name

8248-regret-bounds-for-meta-bayesian-optimization-with-an-unknown-gaussian-process-prior.pdf

Description
Published version
Size

763.32 KB

Format

Adobe PDF

Checksum (MD5)

8f046c747294b8f928ff2d151d65e42c

sword-2019-06-04T15:32:47.original.xml (130 B)
Original SWORD entry document
Author(s)
Kaelbling, Leslie P.
•
Kim, Beomjoon
•
Wang, Zi
Date Issued
2018
Citation
Kaelbling, Leslie P., Kim, Beomjoon and Wang, Zi. 2018. "Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior."
Version
Final published version
Abstract
© 2018 Curran Associates Inc.All rights reserved. Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and probability of improvement achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as the number of offline data and the number of online evaluations increase. Empirically, we have verified our approach on challenging simulated robotic problems featuring task and motion planning.
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2018
PrivacyPermissionsAccessibilityContact us
Notify us about copyright concerns.