Symmetrically Processed Splitting Integrators for Enhanced Hamiltonian Monte Carlo Sampling

Autor: Fernando Casas, Jesús María Sanz-Serna, Sergio Blanes, M. P. Calvo
Přispěvatelé: Blanes, Sergio
Jazyk: angličtina
Rok vydání: 2021
Předmět:
Zdroj: RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname
Repositori Universitat Jaume I
Universitat Jaume I
ISSN: 2019-1049
DOI: 10.1137/20M137940X30
Popis: [EN] We construct integrators to be used in Hamiltonian (or Hybrid) Monte Carlo sampling. The new integrators are easily implementable and, for a given computational budget, may deliver five times as many accepted proposals as standard leapfrog/Verlet without impairing in any way the quality of the samples. They are based on a suitable modification of the processing technique first introduced by Butcher. The idea of modified processing may also be useful for other purposes, like the construction of high-order splitting integrators with positive coefficients.
The first, third, and fourth authors were supported by project PID2019-104927GB-C21 (AEI/FEDER, UE) . The second author was supported by projects PID2019-104927GB-C22 (GNI-QUAMC) , (AEI/FEDER, UE) VA105G18, and VA169P20 (Junta de Castilla y Leon, ES) co-financed by FEDER funds.
Databáze: OpenAIRE