Learning with Errors in Answers to Membership Queries

We study the learning models defined in [AKST97]: 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 [AKST97]. Our algorithm can also handle errors in the equivalence queries.

• Type: Conference
• Year: 2004
• Where: FOCS
• Authors: Laurence Bisht, Nader H. Bshouty, Lawrance Khoury
• Keywords: FOCS 2004, Limited Membership Queries, Malicious Membership Queries, Membership Queries, Theoretical Computer Science