Robust independence testing for constraint-based learning of causal structure

Authors:
Denver Dash;Marek J. Druzdzel
Affiliations:
Decision Systems Laboratory, Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA;Decision Systems Laboratory, Intelligent Systems Program and School of Information Sciences, University of Pittsburgh, Pittsburgh, PA
Venue:
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Year:
2002

Citing 8
Cited 10

A Bayesian Method for the Induction of Probabilistic Networks from Data

Machine Learning
Learning Bayesian Networks: The Combination of Knowledge and Statistical Data

Machine Learning
A tutorial on learning with Bayesian networks

Learning in graphical models
SMILE: Structural Modeling, Inference, and Learning Engine and GeNIe: a development environment for graphical decision-theoretic models

AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
A Simple Constraint-Based Algorithm for Efficiently Mining Observational Databases for Causal Relationships

Data Mining and Knowledge Discovery
Improved learning of Bayesian networks

UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
A hybrid anytime algorithm for the construction of causal models from sparse data

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Learning equivalence classes of Bayesian network structures

UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence

The max-min hill-climbing Bayesian network structure learning algorithm

Machine Learning
Learning Bayesian Networks Based on a Mutual Information Scoring Function and EMI Method

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Part II--Advances in Neural Networks
A Novel Scalable and Data Efficient Feature Subset Selection Algorithm

ECML PKDD '08 Proceedings of the European conference on Machine Learning and Knowledge Discovery in Databases - Part II
Minimum Free Energy Principle for Constraint-Based Learning Bayesian Networks

ECML PKDD '09 Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part I
Bayesian Network Structure Learning by Recursive Autonomy Identification

The Journal of Machine Learning Research
Feature fatigue analysis in product development using Bayesian networks

Expert Systems with Applications: An International Journal
An improved bayesian network learning algorithm based on dependency analysis

CIS'05 Proceedings of the 2005 international conference on Computational Intelligence and Security - Volume Part I
Review: learning bayesian networks: Approaches and issues

The Knowledge Engineering Review
Analysis of Markov Boundary Induction in Bayesian Networks: A New View From Matroid Theory

Fundamenta Informaticae
A multi-objective genetic algorithm approach for solving feature addition problem in feature fatigue analysis

Journal of Intelligent Manufacturing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper considers a method that combines ideas from Bayesian learning, Bayesian network inference, and classical hypothesis testing to produce a more reliable and robust test of independence for constraintbased (CB) learning of causal structure. Our method produces a smoothed contingency table Nxyz that can be used with any test of independence that relies on contingency table statistics. Nxyz can be calculated in the same asymptotic time and space required to calculate a standard contingency table, allows the specification of a prior distribution over parameters, and can be calculated when the database is incomplete. We provide theoretical justification for the procedure, and with synthetic data we demonstrate its benefits empirically over both a CB algorithm using the standard contingency table, and over a greedy Bayesian algorithm. We show that, even when used with noninformative priors, it results in better recovery of structural features and it produces networks with smaller KL-Divergence, especially as the number of nodes increases or the number of records decreases. Another benefit is the dramatic reduction in the probability that a CB algorithm will stall during the search, providing a remedy for an annoying problem plaguing CB learning when the database is small.