A Learning Theoretic Perspective on Local Explainability

In this paper, we explore connections between interpretable machine learning and learning theory through the lens of local approximation explanations. First, we tackle the traditional problem of performance generalization and bound the test-time accuracy of a model using a notion of how locally expl...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-11
Hauptverfasser:	Li, Jeffrey, Nagarajan, Vaishnavh, Plumb, Gregory, Talwalkar, Ameet
Format:	Artikel
Sprache:	eng
Schlagworte:	Approximation Learning theory Machine learning Mathematical analysis Model accuracy
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!