Communications of the ACM
Learning k-term DNF formulas with an incomplete membership oracle
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Exact identification of read-once formulas using fixed points of amplification functions
SIAM Journal on Computing
Randomly Fallible Teachers: Learning Monotone DNF with an Incomplete Membership Oracle
Machine Learning - Special issue on computational learning theory
Learning Fallible Deterministic Finite Automata
Machine Learning - Special issue on COLT '93
Learning from a consistently ignorant teacher
Journal of Computer and System Sciences
Simple learning algorithms using divide and conquer
Computational Complexity
Malicious Omissions and Errors in Answers to Membership Queries
Machine Learning
Learning with queries corrupted by classification noise
Discrete Applied Mathematics
Machine Learning
Machine Learning
On using extended statistical queries to avoid membership queries
The Journal of Machine Learning Research
Learning monotone dnf from a teacher that almost does not answer membership queries
The Journal of Machine Learning Research
Learning attribute-efficiently with corrupt oracles
ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory
Hi-index | 0.00 |
We study the learning models defined in [D. Angluin, M. Krikis, R.H. Sloan, G. Turan, Malicious omissions and errors in answering to membership queries, Machine Learning 28 (2-3) (1997) 211-255]: Learning with equivalence and limited membership queries and learning with equivalence and malicious membership queries. We show that if a class of concepts that is closed under projection is learnable in polynomial time using equivalence and (standard) membership queries then it is learnable in polynomial time in the above models. This closes the open problems in [D. Angluin, M. Krikis, R.H. Sloan, G. Turan, Malicious omissions and errors in answering to membership queries, Machine Learning 28 (2-3) (1997) 211-255]. Our algorithm can also handle errors in the equivalence queries.