arXiv Machine Learning
On the Sample Complexity of Active Learning with Membership Queries
Read the original on arXiv Machine Learning →The paper investigates how the ability to synthesize arbitrary queries (membership queries) changes the sample complexity of active learning compared to the traditional pool-based setting. It shows that some hypothesis classes that only achieve polynomial error decay with pool-based queries become exponentially learnable when synthesis is allowed, revealing a significant gap in learning difficulty. The authors propose sufficient conditions, provide examples, and suggest a conjectural framework to identify classes that benefit from synthesized queries.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.