The Skipping Sampler: A new approach to sample from complex conditional densities

John Moriarty, Jure Vogrinc, Alessandro Zocca

Research output: Contribution to JournalArticleAcademic

20 Downloads (Pure)

Abstract

We introduce the Skipping Sampler, a novel algorithm to efficiently sample from the restriction of an arbitrary probability density to an arbitrary measurable set. Such conditional densities can arise in the study of risk and reliability and are often of complex nature, for example having multiple isolated modes and non-convex or disconnected support. The sampler can be seen as an instance of the Metropolis-Hastings algorithm with a particular proposal structure, and we establish sufficient conditions under which the Strong Law of Large Numbers and the Central Limit Theorem hold. We give theoretical and numerical evidence of improved performance relative to the Random Walk Metropolis algorithm.
Original languageEnglish
JournalarXiv.org
Publication statusPublished - 23 May 2019

Bibliographical note

20 pages, 4 figures

Keywords

  • math.PR
  • math.ST
  • stat.CO
  • stat.TH
  • 65C05, 62F12 (primary) 60F05, 60J05, 65C40 (secondary)

Fingerprint Dive into the research topics of 'The Skipping Sampler: A new approach to sample from complex conditional densities'. Together they form a unique fingerprint.

Cite this