Parameterized learnability of juntas

https://doi.org/10.1016/j.tcs.2009.07.003Get rights and content
Under an Elsevier user license
open archive

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.

Keywords

Learning theory
Computational complexity

Cited by (0)

Work supported by a DST-DAAD project grant for exchange visits. An extended abstract has appeared in Proceedings 28th International Workshop, ALT’07, Sendai, Japan, October 1–4, 2007.