Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experiments

We develop a new, principled algorithm for estimating the contribution of training data points to the behavior of a deep learning model, such as a specific prediction it makes. Our algorithm estimates the AME, a quantity that measures the expected (average) marginal effect of adding a data point to...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-06
Hauptverfasser:	Lin, Jinkun, Zhang, Anqi, Lecuyer, Mathias, Li, Jinyang, Panda, Aurojit, Sen, Siddhartha
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Data points Deep learning Machine learning Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!