Inapproximability of sufficient reasons for decision trees
arXiv:2304.02781v12 citationsh-index: 3
Originality Incremental advance
AI Analysis
This addresses a theoretical limitation in explainable AI for decision trees, showing incremental progress by proving computational hardness.
The paper tackles the problem of approximating the minimal size of δ-sufficient reasons for decision trees, establishing its hardness of approximation.
In this note, we establish the hardness of approximation of the problem of computing the minimal size of a $δ$-sufficient reason for decision trees.