Adaptive rejection sampling with fixed number of nodes

Autor(es)

Martino, L. ^[1] ; Louzada, F. ^[1]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Inst Math Sci & Comp, BR-05508070 Sao Paulo - Brazil

• Tipo de documento: Artigo Científico
• Fonte: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION; v. 48, n. 3, p. 655-665, MAR 16 2019.
• Citações Web of Science: 0

Resumo

The adaptive rejection sampling (ARS) algorithm is a universal random generator for drawing samples efficiently from a univariate log-concave target probability density function (pdf). ARS generates independent samples from the target via rejection sampling with high acceptance rates. Indeed, ARS yields a sequence of proposal functions that converge toward the target pdf, so that the probability of accepting a sample approaches one. However, sampling from the proposal pdf becomes more computational demanding each time it is updated. In this work, we propose a novel ARS scheme, called Cheap Adaptive Rejection Sampling (CARS), where the computational effort for drawing from the proposal remains constant, decided in advance by the user. For generating a large number of desired samples, CARS is faster than ARS. (AU)

• Processo FAPESP: 14/23160-6 - Esquemas eficientes de Monte Carlo para espaços de alta dimensão e grandes bancos de dados médicos e industriais
• Beneficiário: Luca Martino
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado