Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Elements of information theory
Elements of information theory
Learning and robust learning of product distributions
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Stochastic Complexity in Statistical Inquiry Theory
Stochastic Complexity in Statistical Inquiry Theory
Learning Bayesian networks with local structure
UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence
Adaptive Probabilistic Networks with Hidden Variables
Machine Learning - Special issue on learning with probabilistic representations
Using Bayesian networks to analyze expression data
RECOMB '00 Proceedings of the fourth annual international conference on Computational molecular biology
Parameter Learning in Object-Oriented Bayesian Networks
Annals of Mathematics and Artificial Intelligence
Two Models of Information Costs Based on Computational Complexity
Computational Economics
ISMDA '00 Proceedings of the First International Symposium on Medical Data Analysis
A New Measure for the Accuracy of a Bayesian Network
MICAI '02 Proceedings of the Second Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Mining complex models from arbitrarily large databases in constant time
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Learning evaluation functions to improve optimization by local search
The Journal of Machine Learning Research
Fusion of domain knowledge with data for structural learning in object oriented domains
The Journal of Machine Learning Research
Full Bayesian network classifiers
ICML '06 Proceedings of the 23rd international conference on Machine learning
Parallel EDAs to create multivariate calibration models for quantitative chemical applications
Journal of Parallel and Distributed Computing - Special issue on parallel bioinspired algorithms
A New Singly Connected Network Classifier based on Mutual Information
Intelligent Data Analysis
Learning Factor Graphs in Polynomial Time and Sample Complexity
The Journal of Machine Learning Research
HOTOS'05 Proceedings of the 10th conference on Hot Topics in Operating Systems - Volume 10
Sporadic model building for efficiency enhancement of the hierarchical BOA
Genetic Programming and Evolvable Machines
Multimedia ontology learning for automatic annotation and video browsing
MIR '08 Proceedings of the 1st ACM international conference on Multimedia information retrieval
Temporal Bayesian classifiers for modelling muscular dystrophy expression data
Intelligent Data Analysis - Selected papers from IDA2005, Madrid, Spain
Cached sufficient statistics for efficient machine learning with large datasets
Journal of Artificial Intelligence Research
A statistical method for structure learning of Bayesian networks from data
Proceedings of the 2009 International Conference on Hybrid Information Technology
ISBRA'08 Proceedings of the 4th international conference on Bioinformatics research and applications
Automatic model adaptation for complex structured domains
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part II
Learning Non-Stationary Dynamic Bayesian Networks
The Journal of Machine Learning Research
Analysis of epistasis correlation on NK landscapes with nearest-neighbor interactions
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Learning Bayesian nets that perform well
UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence
Learning Bayesian networks with local structure
UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence
Review: learning bayesian networks: Approaches and issues
The Knowledge Engineering Review
Artificial Intelligence in Medicine
Feature subset selection by genetic algorithms and estimation of distribution algorithms
Artificial Intelligence in Medicine
Using literature and data to learn Bayesian networks as clinical models of ovarian tumors
Artificial Intelligence in Medicine
Hi-index | 0.00 |
In recent years there has been an increasing interest in learning Bayesian networks from data. One of the most effective methods for learning such networks is based on the minimum description length (MDL) principle. Previous work has shown that this learning procedure is asymptotically successful: with probability one, it will converge to the target distribution, given a sufficient number of samples. However, the rate of this convergence has been hitherto unknown. In this work we examine the sample complexity of MDL based learning procedures for Bayesian networks. We show that the number of samples needed to learn an ε-close approximation (in terms of entropy distance) with confidence δ is O ((1/ε)4/3 log 1/ε log 1/δ log log 1/δ). This means that the sample complexity is a low-order polynomial in the error threshold and sub-linear in the confidence bound. We also discuss how the constants in this term depend on the complexity of the target distribution. Finally, we address questions of asymptotic minimality and propose a method for using the sample complexity results to speed up the learning process.