Accelerated Sampling on Discrete Spaces with Non-Reversible Markov Processes

12/10/2019
by   Samuel Power, et al.
0

We consider the task of MCMC sampling from a distribution defined on a discrete space. Building on recent insights provided in [Zan19], we devise a class of efficient continuous-time, non-reversible algorithms which make active use of the structure of the underlying space. Particular emphasis is placed on how symmetries and other group-theoretic notions can be used to improve exploration of the space. We test our algorithms on a range of examples from statistics, computational physics, machine learning, and cryptography, which show improvement on alternative algorithms. We provide practical recommendations on how to design and implement these algorithms, and close with remarks on the outlook for both discrete sampling and continuous-time Monte Carlo more broadly.

READ FULL TEXT

page 18

page 19

page 22

page 24

research
07/07/2018

Note on the convergence time of some non-reversible Markov chain Monte Carlo methods

Introduced in statistical physics, non-reversible Markov chain Monte Car...
research
04/19/2020

Zig-zag sampling for discrete structures and non-reversible phylogenetic MCMC

We construct a zig-zag process targeting posterior distributions arising...
research
09/13/2023

Harvesting Brownian Motion: Zero Energy Computational Sampling

The key factor currently limiting the advancement of computational power...
research
08/02/2018

A note on Metropolis-Hasting for sampling across mixed spaces

We are concerned with the Metropolis-Hastings algorithm for sampling acr...
research
10/31/2014

A* Sampling

The problem of drawing samples from a discrete distribution can be conve...
research
02/01/2019

Limit theorems for cloning algorithms

Large deviations for additive path functionals of stochastic processes h...
research
05/05/2022

Identifiability, the KL property in metric spaces, and subgradient curves

Identifiability, and the closely related idea of partial smoothness, uni...

Please sign up or login with your details

Forgot password? Click here to reset