Communications of the ACM
Improved learning of AC0 functions
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
C4.5: programs for machine learning
C4.5: programs for machine learning
Balancing the n-Cube: A Census of Colorings
Journal of Algebraic Combinatorics: An International Journal
Weakly learning DNF and characterizing statistical query learning using Fourier analysis
STOC '94 Proceedings of the twenty-sixth annual ACM symposium on Theory of computing
Learning in the presence of finitely or infinitely many irrelevant attributes
Journal of Computer and System Sciences
Attribute-efficient learning in query and mistake-bound models
Journal of Computer and System Sciences
Adaptive Versus Nonadaptive Attribute-Efficient Learning
Machine Learning
Derandomization Via Small Sample Spaces (Abstract)
SWAT '96 Proceedings of the 5th Scandinavian Workshop on Algorithm Theory
A Brief Outline of Research on Correlation Immune Functions
ACISP '02 Proceedings of the 7th Australian Conference on Information Security and Privacy
On Correlation-Immune Functions
CRYPTO '91 Proceedings of the 11th Annual International Cryptology Conference on Advances in Cryptology
On Learning Correlated Boolean Functions Using Statistical Queries
ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory
Theoretical Computer Science
Proceedings of the thirty-fifth annual ACM symposium on Theory of computing
On the Efficiency of Noise-Tolerant PAC Algorithms Derived from Statistical Queries
Annals of Mathematics and Artificial Intelligence
On using extended statistical queries to avoid membership queries
The Journal of Machine Learning Research
Sequential skewing: an improved skewing algorithm
ICML '04 Proceedings of the twenty-first international conference on Machine learning
New lower bounds for statistical query learning
Journal of Computer and System Sciences - Special issue on COLT 2002
Generalized skewing for functions with continuous and nominal attributes
ICML '05 Proceedings of the 22nd international conference on Machine learning
Why skewing works: learning difficult Boolean functions with greedy tree learners
ICML '05 Proceedings of the 22nd international conference on Machine learning
New Results for Learning Noisy Parities and Halfspaces
FOCS '06 Proceedings of the 47th Annual IEEE Symposium on Foundations of Computer Science
Skewing: an efficient alternative to lookahead for decision tree induction
IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
Performance analysis of a greedy algorithm for inferring Boolean functions
Information Processing Letters
Improved Asymptotic Formulas for Counting Correlation Immune Boolean Functions
SIAM Journal on Discrete Mathematics
Application of a generalization of russo's formula to learning from multiple random oracles
Combinatorics, Probability and Computing
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
Hi-index | 0.00 |
A Boolean function f is correlation immune if each input variable is independent of the output, under the uniform distribution on inputs. For example, the parity function is correlation immune. We consider the problem of identifying relevant variables of a correlation immune function, in the presence of irrelevant variables. We address this problem in two different contexts. First, we analyze Skewing, a heuristic method that was developed to improve the ability of greedy decision tree algorithms to identify relevant variables of correlation immune Boolean functions, given examples drawn from the uniform distribution (Page and Ray, 2003). We present theoretical results revealing both the capabilities and limitations of skewing. Second, we explore the problem of identifying relevant variables in the Product Distribution Choice (PDC) learning model, a model in which the learner can choose product distributions and obtain examples from them. We prove a lemma establishing a property of Boolean functions that may be of independent interest. Using this lemma, we give two new algorithms for finding relevant variables of correlation immune functions in the PDC model.