Open AccessParsimonious adaptive rejection sampling
Author(s) -
Martino L.
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2017.1711
Subject(s) - univariate , sampling (signal processing) , rejection sampling , monte carlo method , computer science , algorithm , importance sampling , sequence (biology) , signal processing , adaptive sampling , sample size determination , sample (material) , mathematics , statistics , machine learning , markov chain monte carlo , digital signal processing , multivariate statistics , hybrid monte carlo , telecommunications , chemistry , chromatography , detector , biology , computer hardware , genetics
Monte Carlo (MC) methods have become very popular in signal processing during the past decades. The adaptive rejection sampling (ARS) algorithms are well‐known MC techniques which draw efficiently independent samples from univariate target densities. The ARS schemes yield a sequence of proposal functions that converge towards the target, so that the probability of accepting a sample approaches one. However, sampling from the proposal pdf becomes more computationally demanding each time it is updated. The parsimonious ARS method, where an efficient trade‐off between acceptance rate and proposal complexity is obtained, is proposed. Thus, the resulting algorithm is faster than the standard ARS approach.