Uniform Characterizations of Polynomial-Query Learnabilities

Authors:
Yosuke Hayashi;Satoshi Matsumoto;Ayumi Shinohara;Masayuki Takeda
Affiliations:
-;-;-;-
Venue:
DS '98 Proceedings of the First International Conference on Discovery Science
Year:
1998

Citing 9
Cited 2

Negative Results for Equivalence Queries

Machine Learning
On the complexity of teaching

Journal of Computer and System Sciences
On the power of equivalence queries

Euro-COLT '93 Proceedings of the first European conference on Computational learning theory
Generalized teaching dimensions and the query complexity of learning

COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Oracles and queries that are sufficient for exact learning

Journal of Computer and System Sciences
How many queries are needed to learn?

Journal of the ACM (JACM)
Queries and Concept Learning

Machine Learning
Queries and Concept Learning

Machine Learning
Oracles in Sigmap2 are Sufficient for Exact Learning

ALT '97 Proceedings of the 8th International Conference on Algorithmic Learning Theory

The Consistency Dimension and Distribution-Dependent Learning from Queries (Extended Abstract)

ALT '99 Proceedings of the 10th International Conference on Algorithmic Learning Theory
Queries Revisited

ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory

Quantified Score

Hi-index	0.02

Visualization

Abstract

We consider the exact learning in the query model. We deal with all types of queries introduced by Angluin: membership, equivalence, superset, subset, disjointness and exhaustiveness queries, and their weak (or restricted) versions where no counterexample is returned. For each of all possible combinations of these queries, we uniformly give complete characterizations of boolean concept classes that are learnable using a polynomial number of polynomial sized queries. Our characterizations show the equivalence between the learnability of a concept class C using queries and the existence of a good query for any subset H of C which is guaranteed to reject a certain fraction of candidate concepts in H regardless of the answer. As a special case for equivalence queries alone, our characterizations directly correspond to the lack of the approximate fingerprint property, which is known to be a sufficient and necessary condition for the learnability using equivalence queries.