Learning regular sets from queries and counterexamples
Information and Computation
Negative Results for Equivalence Queries
Machine Learning
Lower Bound Methods and Separation Results for On-Line Learning Models
Machine Learning - Computational learning theory
Inference of finite automata using homing sequences
Information and Computation
Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle
Machine Learning - Special issue on computational learning theory
Machine Learning
Machine Learning
Learning Monotone DNF from a Teacher That Almost Does Not Answer Membership Queries
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Learning Regular Sets with an Incomplete Membership Oracle
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
How Many Queries Are Needed to Learn One Bit of Information?
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Hi-index | 0.00 |
We consider the model of exact learning using an equivalence oracle and an incomplete membership oracle. In this model, a random subset of the learners membership queries is left unanswered. Our results are as follows. First, we analyze the obvious method for coping with missing answers: search exhaustively through all possible "answer patterns" associated with the unanswered queries. Thereafter, we present two specific concept classes that are efficiently learnable using an equivalence oracle and a (completely reliable) membership oracle, but are provably not polynomially learnable if the membership oracle becomes slightly incomplete. The first class will demonstrate that the aforementioned method of exhaustively searching through all possible answer patterns cannot be substantially improved in general (despite its apparent simplicity). The second class will demonstrate that the incomplete membership oracle can be rendered useless even if it leaves only a fraction 1/poly(n) of all queries unanswered. Finally, we present a learning algorithm for monotone DNF formulas that can cope with a relatively large fraction of missing answers (more than sixty percent), but is as efficient (in terms of run-time and number of queries) as the classical algorithm whose questions are always answered reliably.