The Complexity of Learning Linear Temporal Formulas from Examples
Nathana\"el Fijalkow, Guillaume Lagarde
TL;DR
This paper explores the computational complexity of learning linear temporal logic formulas from examples, providing approximation algorithms and hardness results for various fragments.
Contribution
It introduces the first complexity analysis for learning LTL formulas, including tight bounds and NP-completeness results for key fragments.
Findings
Tight bounds for approximation of the next operator fragment
NP-completeness results for multiple LTL fragments
Approximation algorithms for certain LTL fragments
Abstract
In this paper we initiate the study of the computational complexity of learning linear temporal logic (LTL) formulas from examples. We construct approximation algorithms for fragments of LTL and prove hardness results; in particular we obtain tight bounds for approximation of the fragment containing only the next operator and conjunctions, and prove NP-completeness results for many fragments.
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 · Formal Methods in Verification · Algorithms and Data Compression