Monte Carlo sampling with integrator snippets

Christophe Andrieu, Mauro Camara Escudero, Chang Zhang

Research output: Working paperPreprint

20 Downloads (Pure)

Abstract

Assume interest is in sampling from a probability distribution $\mu$ defined on $(\mathsf{Z},\mathscr{Z})$. We develop a framework to construct sampling algorithms taking full advantage of numerical integrators of ODEs, say $\psi\colon\mathsf{Z}\rightarrow\mathsf{Z}$ for one integration step, to explore $\mu$ efficiently and robustly. The popular Hybrid/Hamiltonian Monte Carlo (HMC) algorithm [Duane, 1987], [Neal, 2011] and its derivatives are example of such a use of numerical integrators. However we show how the potential of integrators can be exploited beyond current ideas and HMC sampling in order to take into account aspects of the geometry of the target distribution. A key idea is the notion of integrator snippet, a fragment of the orbit of an ODE numerical integrator $\psi$, and its associate probability distribution $\bar{\mu}$, which takes the form of a mixture of distributions derived from $\mu$ and $\psi$. Exploiting properties of mixtures we show how samples from $\bar{\mu}$ can be used to estimate expectations with respect to $\mu$. We focus here primarily on Sequential Monte Carlo (SMC) algorithms, but the approach can be used in the context of Markov chain Monte Carlo algorithms as discussed at the end of the manuscript. We illustrate performance of these new algorithms through numerical experimentation and provide preliminary theoretical results supporting observed performance.
Original languageEnglish
PublisherarXiv.org
Number of pages59
DOIs
Publication statusPublished - 20 Apr 2024

Keywords

  • stat.CO
  • stat.ME
  • 65C05, 65C35
  • I.6.8; G.3

Fingerprint

Dive into the research topics of 'Monte Carlo sampling with integrator snippets'. Together they form a unique fingerprint.
  • Approximate Manifold Sampling

    Camara Escudero, M. (Principal Investigator)

    Project: Research

Cite this