Projecting Ising Model Parameters for Fast Mixing

07/03/2014
by   Justin Domke, et al.
0

Inference in general Ising models is difficult, due to high treewidth making tree-based algorithms intractable. Moreover, when interactions are strong, Gibbs sampling may take exponential time to converge to the stationary distribution. We present an algorithm to project Ising model parameters onto a parameter set that is guaranteed to be fast mixing, under several divergences. We find that Gibbs sampling using the projected parameters is more accurate than with the original parameters when interaction strengths are strong and when limited time is available for sampling.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/05/2014

Projecting Markov Random Field Parameters for Fast Mixing

Markov chain Monte Carlo (MCMC) algorithms are simple and extremely powe...
research
09/30/2015

Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets

Inference is typically intractable in high-treewidth undirected graphica...
research
06/30/2021

Perfect Sampling in Infinite Spin Systems via Strong Spatial Mixing

We present a simple algorithm that perfectly samples configurations from...
research
07/19/2018

Approximate Collapsed Gibbs Clustering with Expectation Propagation

We develop a framework for approximating collapsed Gibbs sampling in gen...
research
04/02/2020

Markov Chain-based Sampling for Exploring RNA Secondary Structure under the Nearest Neighbor Thermodynamic Model

We study plane trees as a model for RNA secondary structure, assigning e...
research
05/04/2020

Is the NUTS algorithm correct?

This paper is devoted to investigate whether the popular No U-turn (NUTS...
research
01/16/2013

Inference for Belief Networks Using Coupling From the Past

Inference for belief networks using Gibbs sampling produces a distributi...

Please sign up or login with your details

Forgot password? Click here to reset