Performance analysis of a greedy algorithm for inferring Boolean functions

Authors:
Daiji Fukagawa;Tatsuya Akutsu
Affiliations:
Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan;Bioinformatics Center, Institute for Chemical Research, Kyoto University, Kyoto 611-0011, Japan
Venue:
Information Processing Letters
Year:
2005

Citing 10
Cited 3

On the complexity of inferring functional dependencies

Discrete Applied Mathematics - Special issue on combinatorial problems in databases
Boolean matching using generalized Reed-Muller forms

DAC '94 Proceedings of the 31st annual Design Automation Conference
Randomized algorithms

Randomized algorithms
Selection of relevant features and examples in machine learning

Artificial Intelligence - Special issue on relevance
Approximation algorithms

Approximation algorithms
A Minimization Approach to Propositional Inductive Learning

ECML '95 Proceedings of the 8th European Conference on Machine Learning
Approximating Minimum Keys and Optimal Substructure Screens

COCOON '96 Proceedings of the Second Annual International Conference on Computing and Combinatorics
A simple greedy algorithm for finding functional relations: efficient implementation and average case analysis

Theoretical Computer Science
Learning juntas

Proceedings of the thirty-fifth annual ACM symposium on Theory of computing
Finding Essential Attributes from Binary Data

Annals of Mathematics and Artificial Intelligence

A Trade-Off between Sample Complexity and Computational Complexity in Learning Boolean Networks from Time-Series Data

IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Exploiting Product Distributions to Identify Relevant Variables of Correlation Immune Functions

The Journal of Machine Learning Research
When does greedy learning of relevant attributes succeed?: a fourier-based characterization

COCOON'07 Proceedings of the 13th annual international conference on Computing and Combinatorics

Quantified Score

Hi-index	0.90

Visualization

Abstract

We analyzed average case performance of a known greedy algorithm for inference of a Boolean function from positive and negative examples, and gave a proof to an experimental conjecture that the greedy algorithm works optimally with high probability if both input data and the underlying function are generated uniformly at random.