Title
The consistency dimension and distribution-dependent learning from queries
Abstract
We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses obtained by restricting the instance space. Then we propose and study two models of query learning in which there is a probability distribution on the instance space, both as an application of the tools developed from the combinatorial characterization and as models of independent interest.
Year
DOI
Venue
2002
10.1016/S0304-3975(01)00400-5
Theor. Comput. Sci.
Keywords
DocType
Volume
probability distribution
Journal
288
Issue
ISSN
Citations 
2
0304-3975
12
PageRank 
References 
Authors
1.12
9
4
Name
Order
Citations
PageRank
José L. Balcázar170162.06
Jorge Castro2181.80
David Guijarro3272.44
Hans-Ulrich Simon4567104.52