Adaptive Magnetic Hamiltonian Monte Carlo

Magnetic Hamiltonian Monte Carlo (MHMC) is a Markov Chain Monte Carlo method that expands on Hamiltonian Monte Carlo (HMC) by adding a magnetic field to Hamiltonian dynamics. This magnetic field offers a great deal of flexibility over HMC and encourages more efficient exploration of the target poste...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Wilson Tsakane Mongwe, Rendani Mbuvha, Tshilidzi Marwala
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/11741b05895b4cef99bef5d3b1f5ec8a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:11741b05895b4cef99bef5d3b1f5ec8a
record_format dspace
spelling oai:doaj.org-article:11741b05895b4cef99bef5d3b1f5ec8a2021-11-20T00:03:07ZAdaptive Magnetic Hamiltonian Monte Carlo2169-353610.1109/ACCESS.2021.3127931https://doaj.org/article/11741b05895b4cef99bef5d3b1f5ec8a2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9614186/https://doaj.org/toc/2169-3536Magnetic Hamiltonian Monte Carlo (MHMC) is a Markov Chain Monte Carlo method that expands on Hamiltonian Monte Carlo (HMC) by adding a magnetic field to Hamiltonian dynamics. This magnetic field offers a great deal of flexibility over HMC and encourages more efficient exploration of the target posterior. This results in faster convergence and lower autocorrelations in the generated samples compared to HMC. However, as with HMC, MHMC is sensitive to the user specified trajectory length and step size. Automatically setting the parameters of MHMC is yet to be considered in the literature. In this work, we present the Adaptive MHMC (A-MHMC) algorithm which extends MHMC in that it automatically sets the parameters of MHMC and thus eliminates the need for the user to manually set a trajectory length and step size. The trajectory length adaptation is based on an extension of the No-U-Turn Sampler (NUTS) methodology to incorporate the magnetic field present in MHMC, while the step size is set via dual averaging during the burn-in period. Empirical results based on experiments performed on jump diffusion processes calibrated to real world financial market data, a simulation study using multivariate Gaussian distributions and real world benchmark datasets modelled using Bayesian Logistic Regression show that A-MHMC outperforms MHMC and NUTS on an effective sample size basis. In addition, A-MHMC provides significant relative speed up (up to 40 times) over MHMC and produces similar time normalised effective samples sizes relative to NUTS.Wilson Tsakane MongweRendani MbuvhaTshilidzi MarwalaIEEEarticleBayesian logistic regressionjump diffusion processesadaptiveMagnetic Hamiltonian Monte CarloMarkov Chain Monte CarloElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152993-153003 (2021)
institution DOAJ
collection DOAJ
language EN
topic Bayesian logistic regression
jump diffusion processes
adaptive
Magnetic Hamiltonian Monte Carlo
Markov Chain Monte Carlo
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Bayesian logistic regression
jump diffusion processes
adaptive
Magnetic Hamiltonian Monte Carlo
Markov Chain Monte Carlo
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Wilson Tsakane Mongwe
Rendani Mbuvha
Tshilidzi Marwala
Adaptive Magnetic Hamiltonian Monte Carlo
description Magnetic Hamiltonian Monte Carlo (MHMC) is a Markov Chain Monte Carlo method that expands on Hamiltonian Monte Carlo (HMC) by adding a magnetic field to Hamiltonian dynamics. This magnetic field offers a great deal of flexibility over HMC and encourages more efficient exploration of the target posterior. This results in faster convergence and lower autocorrelations in the generated samples compared to HMC. However, as with HMC, MHMC is sensitive to the user specified trajectory length and step size. Automatically setting the parameters of MHMC is yet to be considered in the literature. In this work, we present the Adaptive MHMC (A-MHMC) algorithm which extends MHMC in that it automatically sets the parameters of MHMC and thus eliminates the need for the user to manually set a trajectory length and step size. The trajectory length adaptation is based on an extension of the No-U-Turn Sampler (NUTS) methodology to incorporate the magnetic field present in MHMC, while the step size is set via dual averaging during the burn-in period. Empirical results based on experiments performed on jump diffusion processes calibrated to real world financial market data, a simulation study using multivariate Gaussian distributions and real world benchmark datasets modelled using Bayesian Logistic Regression show that A-MHMC outperforms MHMC and NUTS on an effective sample size basis. In addition, A-MHMC provides significant relative speed up (up to 40 times) over MHMC and produces similar time normalised effective samples sizes relative to NUTS.
format article
author Wilson Tsakane Mongwe
Rendani Mbuvha
Tshilidzi Marwala
author_facet Wilson Tsakane Mongwe
Rendani Mbuvha
Tshilidzi Marwala
author_sort Wilson Tsakane Mongwe
title Adaptive Magnetic Hamiltonian Monte Carlo
title_short Adaptive Magnetic Hamiltonian Monte Carlo
title_full Adaptive Magnetic Hamiltonian Monte Carlo
title_fullStr Adaptive Magnetic Hamiltonian Monte Carlo
title_full_unstemmed Adaptive Magnetic Hamiltonian Monte Carlo
title_sort adaptive magnetic hamiltonian monte carlo
publisher IEEE
publishDate 2021
url https://doaj.org/article/11741b05895b4cef99bef5d3b1f5ec8a
work_keys_str_mv AT wilsontsakanemongwe adaptivemagnetichamiltonianmontecarlo
AT rendanimbuvha adaptivemagnetichamiltonianmontecarlo
AT tshilidzimarwala adaptivemagnetichamiltonianmontecarlo
_version_ 1718419819785617408