Sciweavers

79
Voted
COLT
2008
Springer

On the Power of Membership Queries in Agnostic Learning

14 years 10 months ago
On the Power of Membership Queries in Agnostic Learning
We study the properties of the agnostic learning framework of Haussler [Hau92] and Kearns, Schapire and Sellie [KSS94]. In particular, we address the question: is there any situation in which membership queries are useful in agnostic learning? Our results show that the answer is negative for distribution-independent agnostic learning and positive for agnostic learning with respect to a specific marginal distribution. Namely, we give a simple proof that any concept class learnable agnostically by a distribution-independent algorithm with access to membership queries is also learnable agnostically without membership queries. This resolves an open problem posed by Kearns et al. [KSS94]. For agnostic learning with respect to the uniform distribution over {0, 1}n we show a concept class that is learnable with membership queries but computationally hard to learn from random examples alone (assuming that one-way functions exist).
Vitaly Feldman
Added 18 Oct 2010
Updated 18 Oct 2010
Type Conference
Year 2008
Where COLT
Authors Vitaly Feldman
Comments (0)