Number of the records: 1
Adaptive multiple importance sampling for Gaussian processes
- 1.
SYSNO ASEP 0469804 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Adaptive multiple importance sampling for Gaussian processes Author(s) Xiong, X. (GB)
Šmídl, Václav (UTIA-B) RID, ORCID
Filippone, M. (FR)Number of authors 3 Source Title Journal of Statistical Computation and Simulation. - : Taylor & Francis - ISSN 0094-9655
Roč. 87, č. 8 (2017), s. 1644-1665Number of pages 22 s. Publication form Print - P Language eng - English Country GB - United Kingdom Keywords Gaussian Process ; Bayesian estimation ; Adaptive importance sampling Subject RIV BB - Applied Statistics, Operational Research OECD category Statistics and probability R&D Projects 7F14287 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) Institutional support UTIA-B - RVO:67985556 UT WOS 000399503500009 EID SCOPUS 85010689209 DOI 10.1080/00949655.2017.1280037 Annotation In applications of Gaussian processes (GPs) where quantification of uncertainty is a strict requirement, it is necessary to accurately characterize the posterior distribution over Gaussian process covariance parameters. This is normally done by means of standard Markov chain Monte Carlo (MCMC) algorithms, which require repeated expensive calculations involving the marginal likelihood. Motivated by the desire to avoid the inefficiencies of MCMC algorithms rejecting a considerable amount of expensive proposals, this paper develops an alternative inference framework based on adaptive multiple importance sampling (AMIS). In particular, this paper studies the application of AMIS for GPs in the case of a Gaussian likelihood, and proposes a novel pseudo-marginal-based AMIS algorithm for non-Gaussian likelihoods, where the marginal likelihood is unbiasedly estimated. The results suggest that the proposed framework outperforms MCMC-based inference of covariance parameters in a wide range of scenarios. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2018
Number of the records: 1