Suscripción a Biblioteca: Guest
Portal Digitalde Biblioteca Digital eLibros Revistas Referencias y Libros de Ponencias Colecciones
International Journal for Uncertainty Quantification
Factor de Impacto: 3.259 Factor de Impacto de 5 años: 2.547 SJR: 0.417 SNIP: 0.8 CiteScore™: 1.52

ISSN Imprimir: 2152-5080
ISSN En Línea: 2152-5099

Acceso abierto

International Journal for Uncertainty Quantification

DOI: 10.1615/Int.J.UncertaintyQuantification.2016018590
pages 341-359

TRANSITIONAL ANNEALED ADAPTIVE SLICE SAMPLING FOR GAUSSIAN PROCESS HYPER-PARAMETER ESTIMATION

Alfredo Garbuno-Inigo
Institute for Risk and Uncertainty, School of Engineering, University of Liverpool, Brownlow Hill, Liverpool, L69 3GH, United Kingdom
F. A. DiazDelaO
Institute for Risk and Uncertainty, School of Engineering, University of Liverpool, Brownlow Hill, Liverpool, L69 3GH, United Kingdom
Konstantin M. Zuev
Department of Computing and Mathematical Sciences, Division of Engineering and Applied Science, 1200 E California Blvd., California Institute of Technology, Pasadena, California 91125, USA

SINOPSIS

Surrogate models have become ubiquitous in science and engineering for their capability of emulating expensive computer codes, necessary to model and investigate complex phenomena. Bayesian emulators based on Gaussian processes adequately quantify the uncertainty that results from the cost of the original simulator, and thus the inability to evaluate it on the whole input space. However, it is common in the literature that only a partial Bayesian analysis is carried out, whereby the underlying hyper-parameters are estimated via gradient-free optimization or genetic algorithms, to name a few methods. On the other hand, maximum a posteriori (MAP) estimation could discard important regions of the hyper-parameter space. In this paper, we carry out a more complete Bayesian inference, that combines Slice Sampling with some recently developed sequential Monte Carlo samplers. The resulting algorithm improves the mixing in the sampling through the delayed-rejection nature of Slice Sampling, the inclusion of an annealing scheme akin to Asymptotically Independent Markov Sampling and parallelization via transitional Markov chain Monte Carlo. Examples related to the estimation of Gaussian process hyper-parameters are presented. For the purpose of reproducibility, further development, and use in other applications, the code to generate the examples in this paper is freely available for download at http://github.com/agarbuno/ta2s2_codes.


Articles with similar content:

EMBEDDED MODEL ERROR REPRESENTATION FOR BAYESIAN MODEL CALIBRATION
International Journal for Uncertainty Quantification, Vol.9, 2019, issue 4
Habib N. Najm, Xun Huan, Khachik Sargsyan
ANALYSIS OF VARIANCE-BASED MIXED MULTISCALE FINITE ELEMENT METHOD AND APPLICATIONS IN STOCHASTIC TWO-PHASE FLOWS
International Journal for Uncertainty Quantification, Vol.4, 2014, issue 6
Guang Lin, Yalchin Efendiev, Lijian Jiang, Jia Wei
ROBUSTNESS OF WILKS' CONSERVATIVE ESTIMATE OF CONFIDENCE INTERVALS
International Journal for Uncertainty Quantification, Vol.5, 2015, issue 6
Jan Peter Hessling, Jeffrey Uhlmann
HIERARCHICAL SPARSE BAYESIAN LEARNING FOR STRUCUTRAL HEALTH MONITORING WITH INCOMPLETE MODAL DATA
International Journal for Uncertainty Quantification, Vol.5, 2015, issue 2
Yong Huang, James L. Beck
ASYMPTOTICALLY INDEPENDENT MARKOV SAMPLING: A NEW MARKOV CHAIN MONTE CARLO SCHEME FOR BAYESIAN INFERENCE
International Journal for Uncertainty Quantification, Vol.3, 2013, issue 5
James L. Beck, Konstantin M. Zuev