Online Program Home
My Program

Abstract Details

Activity Number: 427
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Computing
Abstract #319032 View Presentation
Title: A Repulsive-Attractive Metropolis Algorithm for Multimodality
Author(s): Hyungsuk Tak* and Xiao-Li Meng and David A. van Dyk
Companies: Harvard and Harvard and Imperial College London
Keywords: Auxiliary variable ; Forced Metropolis algorithm ; Equi-energy sampler ; Tempered transitions ; Parallel tempering ; Markov chain Monte Carlo

We propose a repulsive-attractive Metropolis algorithm that expedites a Markov chain's jumping between modes of a multi-modal distribution in a simple and fast manner. This algorithm is essentially a Metropolis-Hastings algorithm with a proposal that consists of a downhill move in density that aims to make local modes repulsive, followed by an uphill move in density that aims to make local modes attractive. The downhill move is achieved via a reciprocal Metropolis ratio so that the algorithm prefers downward movement. The uphill move does the opposite using the standard Metropolis ratio which prefers upward movement. This down-up movement in density increases the probability of a proposed move to a different mode. Because the acceptance probability of the proposal involves a ratio of intractable integrals, we introduce an auxiliary variable which introduces a term that cancels with the intractable ratio. Using two examples, we demonstrate the potential for the proposed algorithm to explore a multi-modal distribution more effectively and with less tuning than is commonly required by tempering-based methods.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association