AFP Algorithm and a Canonical Normal Form for Horn Formulas
Ruhollah Majdoddin
TL;DR
This paper introduces a canonical normal form for Horn formulas and demonstrates that the AFP Algorithm's output is in this form, while analyzing its complexity and refinement process.
Contribution
It presents a canonical normal form for Horn formulas and proves the AFP Algorithm's output adheres to this form, with analysis of its complexity.
Findings
AFP Algorithm's complexity is not improved by multiple refinements after negative counterexamples.
The paper defines a canonical normal form for Horn formulas.
The AFP Algorithm's output is shown to be in this normal form.
Abstract
AFP Algorithm is a learning algorithm for Horn formulas. We show that it does not improve the complexity of AFP Algorithm, if after each negative counterexample more that just one refinements are performed. Moreover, a canonical normal form for Horn formulas is presented, and it is proved that the output formula of AFP Algorithm is in this normal form.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Algorithms and Data Compression · semigroups and automata theory