SOTAVerified

Importance Weight Estimation and Generalization in Domain Adaptation under Label Shift

2020-11-29Code Available0· sign in to hype

Kamyar Azizzadenesheli

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We study generalization under labeled shift for categorical and general normed label spaces. We propose a series of methods to estimate the importance weights from labeled source to unlabeled target domain and provide confidence bounds for these estimators. We deploy these estimators and provide generalization bounds in the unlabeled target domain.

Tasks

Reproductions