Parameterized Learnability of k-Juntas and Related Problems

Authors:
Vikraman Arvind;Johannes Köbler;Wolfgang Lindner
Affiliations:
The Institute of Mathematical Sciences, Chennai 600 113, India;Institut für Informatik, Humboldt Universität zu Berlin, Germany;Sidonia Systems, Grubmühl 20, D-82131 Stockdorf, Germany
Venue:
ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Year:
2007

Citing 21
Cited 0

A theory of the learnable

Communications of the ACM
NP is as easy as detecting unique solutions

Theoretical Computer Science
Occam's razor

Information Processing Letters
Learning regular sets from queries and counterexamples

Information and Computation
Quantifying inductive bias: AI learning algorithms and Valiant's learning framework

Artificial Intelligence
Computational limitations on learning from examples

Journal of the ACM (JACM)
Learning decision trees using the Fourier spectrum

SIAM Journal on Computing
Parameterized learning complexity

COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Learning Boolean concepts in the presence of many irrelevant features

Artificial Intelligence
An introduction to computational learning theory

An introduction to computational learning theory
Fixed-Parameter Tractability and Completeness I: Basic Results

SIAM Journal on Computing
Fast learning of k-term DNF formulas with queries

Journal of Computer and System Sciences - Special issue on selected papers presented at the 24th annual ACM symposium on the theory of computing (STOC '92)
Oracles and queries that are sufficient for exact learning

Journal of Computer and System Sciences
On the Fourier spectrum of monotone functions

Journal of the ACM (JACM)
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
Fixed-Parameter Complexity and Cryptography

AAECC-10 Proceedings of the 10th International Symposium on Applied Algebra, Algebraic Algorithms and Error-Correcting Codes
Learning juntas

Proceedings of the thirty-fifth annual ACM symposium on Theory of computing
On the Fourier Spectrum of Symmetric Boolean Functions with Applications to Learning Symmetric Juntas

CCC '05 Proceedings of the 20th Annual IEEE Conference on Computational Complexity
Parameterized Complexity Theory (Texts in Theoretical Computer Science. An EATCS Series)

Parameterized Complexity Theory (Texts in Theoretical Computer Science. An EATCS Series)
Approximation algorithms for combinatorial problems

Journal of Computer and System Sciences
Parameterized Complexity

Parameterized Complexity

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the parameterized complexity of learning k-juntas and some variations of juntas. We show the hardness of learning k-juntas and subclasses of k-juntas in the PAC model by reductions from a W[2]-complete problem. On the other hand, as a consequence of a more general result we show that k-juntas are exactly learnable with improper equivalence queries and access to a W[P] oracle.