English

Query-driven PAC-Learning for Reasoning

Artificial Intelligence 2019-06-25 v1

Abstract

We consider the problem of learning rules from a data set that support a proof of a given query, under Valiant's PAC-Semantics. We show how any backward proof search algorithm that is sufficiently oblivious to the contents of its knowledge base can be modified to learn such rules while it searches for a proof using those rules. We note that this gives such algorithms for standard logics such as chaining and resolution.

Keywords

Cite

@article{arxiv.1906.10118,
  title  = {Query-driven PAC-Learning for Reasoning},
  author = {Brendan Juba},
  journal= {arXiv preprint arXiv:1906.10118},
  year   = {2019}
}

Comments

In Fourth International Workshop on Declarative Learning Based Programming (DeLBP 2019)

R2 v1 2026-06-23T10:02:15.091Z