Learning read-once formulas using membership queries
COLT '89 Proceedings of the second annual workshop on Computational learning theory
Cryptographic limitations on learning Boolean formulae and finite automata
Journal of the ACM (JACM)
A framework for polynomial-time query learnability
Mathematical Systems Theory
Structural analysis of polynomial-time query learnability
Mathematical Systems Theory
When won't membership queries help?
Selected papers of the 23rd annual ACM symposium on Theory of computing
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)
Complexity theoretic hardness results for query learning
Computational Complexity
Machine Learning
Machine Learning
A General Dimension for Exact Learning
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Abstract Combinatorial Characterizations of Exact Learning via Queries
COLT '00 Proceedings of the Thirteenth Annual Conference on Computational Learning Theory
Hi-index | 0.00 |
We use the notion of general dimension to show that any p-evaluatable concept class withp olynomial query complexity can be learned in polynomial time with the help of an oracle in the polynomial hierarchy, where the complexity of the required oracle depends on the query-types used by the learning algorithm. In particular, we show that for subset and superset queries an oracle in 驴3P suffices. Since the concept class of DNF formulas has polynomial query complexity with respect to subset and superset queries with DNF formulas as hypotheses, it follows that DNF formulas are properly learnable in polynomial time with subset and superset queries and the help of an oracle in 驴3P. We also show that the required oracle in our main theorem cannot be replaced by an oracle in a lower level of the polynomial-time hierarchy, unless the hierarchy collapses.