Monte Carlo inference via greedy importance sampling

Monte Carlo inference via greedy importance sampling (2000)

Cached

Download Links

[logos.uwaterloo.ca]

Other Repositories/Bibliography

DBLP

by Dale Schuurmans , Finnegan Southey

Venue:	In Proceedings UAI
Citations:	3 - 1 self

BibTeX

@INPROCEEDINGS{Schuurmans00montecarlo,
    author = {Dale Schuurmans and Finnegan Southey},
    title = {Monte Carlo inference via greedy importance sampling},
    booktitle = {In Proceedings UAI},
    year = {2000},
    pages = {523--532},
    publisher = {Morgan Kaufmann Publishers}
}

Bookmark

OpenURL

Abstract

We present a new method for conducting Monte Carlo inference in graphical models which combines explicit search with generalized importance sampling. The idea is to reduce the variance of importance sampling by searching for significant points in the target distribution. We prove that it is possible to introduce search and still maintain unbiasedness. We then demonstrate our procedure on a few simple inference tasks and show that it can improve the inference quality of standard MCMC methods, including Gibbs sampling, Metropolis sampling, and Hybrid Monte Carlo. This paper extends previous work which showed how greedy importance sampling could be correctly realized in the one-dimensional case. 1 Introduction It is well known that general inference and learning with Bayesian networks is computationally hard [DL93, Rot93], and it is therefore necessary to consider restricted architectures [Pea88], or heuristic and approximate algorithms to perform these tasks [JGJS98, Fre9...

Citations

6514	Elements of Information Theory - Cover, Thomas - 1991
5664	Probabilistic Reasoning in Intelligent Systems - Pearl - 1988
656	An Introduction to Variational Methods for Graphical Models - Jordan, Ghahramani, et al. - 1999
513	Bayesian Learning for Neural Networks - Neal - 1996
496	The computational complexity of probabilistic inference using bayesian belief networks - Cooper - 1990
488	A: Visual tracking by stochastic propagation of conditional density - Isard, Blake - 1996
449	Probabilistic inference using Markov chain Monte Carlo methods - Neal - 1993
426	D.: Markov chain Monte Carlo in practice - Gilks, Richardson, et al. - 1996
313	Simulation and the Monte Carlo Method - Rubinstein - 1981
249	Bayesian Inference in Econometric Models Using Monte Carlo Integration, Econometrica 57 (6 - Geweke - 1989
220	Approximating probabilistic inference in Bayesian belief networks is NP-hard - Dagum, Luby - 1993
210	Graphical Models for Machine Learning and Digital Communication - Frey - 1998
158	Propagating uncertainty in Bayesian networks by probabilistic logic sampling, in - Henrion - 1988
142	Simulation approaches to general probabilistic inference on belief networks - Shachter, Peot - 1989
137	Stochastic simulation algorithms for dynamic probabilistic networks - Kanazawa, Koller, et al. - 1995
129	Introduction to Monte Carlo Methods - MacKay - 1998
114	Real analysis and probability - Ash - 1972
112	Tools for Statistical Inference: Methods for the Exploration of Posterior Distributions and Likelihood Functions” Springer Series in Statistics - Tanner - 1996
40	An optimal approximation algorithm for bayesian inference - Dagum, Luby - 1997
39	Backward simulation in Bayesian networks - Fung, Favero, et al. - 1994
19	A stratified simulation scheme for inference in Bayesian belief networks - Bouckaert - 1994
11	Importance sampling algorithms for the propagation of probabilities in belief networks - Cano, Hernandez, et al. - 1996
6	Regularized greedy importance sampling - Southey, Schuurmans, et al. - 2002
4	Chaining via annealing. Ann Statist - Evans - 1991
3	On the hardness of approximating approximate reasoning - Roth - 1993