Parallel Gaussian process surrogate Bayesian inference with noisy likelihood evaluations

Tutkimustuotos: LehtiartikkeliArticleScientificvertaisarvioitu

3 Sitaatiot (Scopus)
23 Lataukset (Pure)

Abstrakti

We consider Bayesian inference when only a limited number of noisy log-likelihood evaluations can be obtained. This occurs for example when complex simulator-based statistical models are fitted to data, and synthetic likelihood (SL) method is used to form the noisy log-likelihood estimates using computationally costly forward simulations. We frame the inference task as a sequential Bayesian experimental design problem, where the log-likelihood function is modelled with a hierarchical Gaussian process (GP) surrogate model, which is used to efficiently select additional log-likelihood evaluation locations. Motivated by recent progress in the related problem of batch Bayesian optimisation, we develop various batch-sequential design strategies which allow to run some of the potentially costly simulations in parallel. We analyse the properties of the resulting method theoretically and empirically. Experiments with several toy problems and simulation models suggest that our method is robust, highly parallelisable, and sample-efficient.
AlkuperäiskieliEnglanti
Sivut147-178
Sivumäärä32
JulkaisuBayesian Analysis
Vuosikerta16
Numero1
DOI - pysyväislinkit
TilaJulkaistu - maaliskuuta 2021
OKM-julkaisutyyppiA1 Julkaistu artikkeli, soviteltu

Sormenjälki

Sukella tutkimusaiheisiin 'Parallel Gaussian process surrogate Bayesian inference with noisy likelihood evaluations'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä