A General Theoretical Framework for Learning Smallest Interpretable Models

Sebastian Ordyniak

doi:10.1016/j.artint.2025.104441

A General Theoretical Framework for Learning Smallest Interpretable Models

2025-10-26

0

OA

AI

DOI：10.1016/j.artint.2025.104441

Original

Save

View PDF

Abstract

En 中文

We develop a general algorithmic framework that allows us to obtain fixed-parameter tractability for computing smallest symbolic models that represent given data. Our framework applies to all ML model types that admit a certain extension property. By establishing this extension property for decision trees, decision sets, decision lists, and binary decision diagrams, we obtain that minimizing these fundamental model types is fixed-parameter tractable. Our framework even applies to ensembles, which combine individual models by majority decision.

Keywords:

aaa

abc

aac

A General Theoretical Framework for Learning Smallest Interpretable Models

Abstract

AI Summary

Journal

Organization