Efficient markov network structure discovery using independence tests

Efficient markov network structure discovery using independence tests (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Facundo Bromberg , Dimitris Margaritis , Vasant Honavar

Venue:	In Proc SIAM Data Mining
Citations:	11 - 0 self

BibTeX

@INPROCEEDINGS{Bromberg06efficientmarkov,
    author = {Facundo Bromberg and Dimitris Margaritis and Vasant Honavar},
    title = {Efficient markov network structure discovery using independence tests},
    booktitle = {In Proc SIAM Data Mining},
    year = {2006},
    pages = {06}
}

Bookmark

OpenURL

Abstract

We present two algorithms for learning the structure of a Markov network from discrete data: GSMN and GSIMN. Both algorithms use statistical conditional independence tests on data to infer the structure by successively constraining the set of structures consistent with the results of these tests. GSMN is a natural adaptation of the Grow-Shrink algorithm of Margaritis and Thrun for learning the structure of Bayesian networks. GSIMN extends GSMN by additionally exploiting Pearl’s well-known properties of conditional independence relations to infer novel independencies from known independencies, thus avoiding the need to perform these tests. Experiments on artificial and real data sets show GSIMN can yield savings of up to 70 % with respect to GSMN, while generating a Markov network with comparable or in several cases considerably improved quality. In addition

Citations

7320	Introduction to Algorithms - CORMEN, LEISERSON, et al. - 1985
5662	Probabilistic reasoning in intelligent systems: networks of plausible inference - Pearl - 1988
3011	Stochastic Relaxation, Gibbs Distributions and the Bayesian Restoration of Images - Geman, Geman - 1984
912	Spatial interaction and the statistical analysis of lattice systems - Besag - 1974
845	Graphical models - Lauritzen - 1996
825	A: Categorical data analysis - Agresti - 1990
751	Learning Bayesian networks: the combination of knowledge and statistical data - Heckerman, Geiger, et al. - 1995
558	On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games - Dung - 1995
530	D: Using Bayesian networks to analyze expression data - Friedman, Linial, et al.
517	UCI repository of machine learning databases - Hettich, Merz - 1998
507	An Introduction to Computational Learning Theory - Kearns, Vazirani - 1994
487	Approximating discrete probability distributions with dependence trees - Chow, Liu - 1968
464	Inducing features of random fields - Pietra, S, et al. - 1997
301	Toward optimal feature selection - Koller, Sahami - 1996
253	A PolynomialTime Approximation Algorithm for the Permanent of a Matrix with Nonnegative Entries - Jerrum, Sinclair, et al.
247	A tutorial on learning Bayesian networks - Heckerman - 1995
212	Operations for learning with graphical models - Buntine - 1994
174	Bayesian image restoration, with two applications in spatial statistics. Ann Inst Stat Math 43(1):1–59 - Besag, York, et al. - 1991
163	Learning Bayesian belief networks: An approach based on the MDL principle - Lam, Bacchus - 1994
147	Conditional independence in statistical theory - Dawid - 1979
142	Efficiently inducing features or conditional random fields - McCallum - 2003
141	An introduction to mcmc for machine learning - Andrieu, Freitas, et al.
104	On the computational complexity of Ising spin glass models - Barahona - 1982
104	A model for belief revision - Martins, Shapiro - 1988
98	Sparse graphical models for exploring gene expression data - Dobra, Hans, et al. - 2004
92	Strimmer K: An empirical Bayes approach to inferring large-scale gene association networks - Schafer
77	How to reason defeasibly - Pollock - 1992
66	Defeat among arguments: a system of defeasible inference - Loui - 1987
65	Discriminative learning of markov random fields for segmentation of 3d range data - Anguelov, Taskar, et al. - 2005
64	PAMPAS: Real-valued graphical models for computer vision - Isard
57	A reasoning model based on the production of acceptable arguments - Amgoud, Cayrol
50	Categorical data analysis. 2nd edition - Agresti
50	Graphoids: a graph-based logic for reasoning about relevance relations - Pearl, Paz - 1987
50	Logical Tools for Modelling Legal Argument. A Study of Defeasible Argumentation - Prakken - 1997
43	Bayesian network induction via local neighborhoods - Margaritis, Thrun - 1999
42	The recovery of causal poly-trees from statistical data - Rebane, Pearl - 1989
39	Learning Markov networks: Maximum bounded tree-width graphs - Karger, Srebro - 2001
39	The max-min hill-climbing Bayesian network structure learning algorithm - Tsamardinos, Brown, et al.
38	D: Active Learning for Structure in Bayesian Networks - Tong, Koller
32	Learning factor graphs in polynomial time and sample complexity - Abbeel, Koller, et al.
29	Stochastic Independence, Causal Independence, and Shieldability - Spohn - 1980
26	Propagation of uncertainty by probabilistic logic sampling in Bayes’ networks - Henrion - 1988
25	HITON: A novel Markov blanket algorithm for optimal variable selection - Aliferis, Tsamardinos, et al. - 2003
24	Some methods for strengthening the common χ 2 tests. Biometrics 10:417–451 - Cochran - 1954
23	Nonlinear markov networks for continuous variables - Hofmann, Tresp - 1998
22	Random generation of Bayesian networks - Ide, Cozman - 2002
21	Time and sample efficient discovery of markov blankets and direct causal relations - Tsamardinos, Aliferis, et al. - 2003
20	Algorithms for large scale markov blanket discovery - Tsamardinos, Aliferis, et al. - 2003
19	A robust procedure for gaussian graphical models search for microarray data with p larger than n - Castello, Roverato - 2006
15	An introduction to spatial point processes and Markov random fields - Isham - 1981