MCMC‐driven importance samplers

•We introduce different possible combinations of Markov Chain Monte Carlo algorithms and importance sampling schemes.•The different variants address computational challenges arising in real-world applications.•We introduce different strategies for designing cheaper schemes, for instance, recycling s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied mathematical modelling Ročník 111; s. 310 - 331
Hlavní autoři: Llorente, F., Curbelo, E., Martino, L., Elvira, V., Delgado, D.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.11.2022
Témata:
Bayesian inference
Computational algorithms
Importance sampling
Quadrature methods
Bayesian inference
Computational algorithms
Quadrature methods
Importance sampling
ISSN:0307-904X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•We introduce different possible combinations of Markov Chain Monte Carlo algorithms and importance sampling schemes.•The different variants address computational challenges arising in real-world applications.•We introduce different strategies for designing cheaper schemes, for instance, recycling samples.•Numerical experiments show the benefits of the proposed schemes as compared to other benchmark methods.•Related Matlab and Python code is also available. Monte Carlo sampling methods are the standard procedure for approximating complicated integrals of multidimensional posterior distributions in Bayesian inference. In this work, we focus on the class of layered adaptive importance sampling algorithms, which is a family of adaptive importance samplers where Markov chain Monte Carlo algorithms are employed to drive an underlying multiple importance sampling scheme. The modular nature of the layered adaptive importance sampling scheme allows for different possible implementations, yielding a variety of different performances and computational costs. In this work, we propose different enhancements of the classical layered adaptive importance sampling setting in order to increase the efficiency and reduce the computational cost, of both upper and lower layers. The different variants address computational challenges arising in real-world applications, for instance with highly concentrated posterior distributions. Furthermore, we introduce different strategies for designing cheaper schemes, for instance, recycling samples generated in the upper layer and using them in the final estimators in the lower layer. Different numerical experiments show the benefits of the proposed schemes, comparing with benchmark methods presented in the literature, and in several challenging scenarios.
ISSN:0307-904X
DOI:10.1016/j.apm.2022.06.027