Importance Weight Estimation and Generalization in Domain Adaptation Under Label Shift
- 2 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (10) , 6578-6584
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.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Domain adaptation and sample bias correction theory and algorithm for regressionTheoretical Computer Science, 2014
- User-Friendly Tail Bounds for Sums of Random MatricesFoundations of Computational Mathematics, 2011
- A theory of learning from different domainsMachine Learning, 2009
- Quantifying counts and costs via classificationData Mining and Knowledge Discovery, 2008
- Adjusting the Outputs of a Classifier to New aPrioriProbabilities: A Simple ProcedureNeural Computation, 2002
- Improving predictive inference under covariate shift by weighting the log-likelihood functionJournal of Statistical Planning and Inference, 2000
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- An Approach to Inequalities for the Distributions of Infinite-Dimensional Martingales1992
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Über Die Praktische Auflösung von Integralgleichungen mit Anwendungen auf RandwertaufgabenActa Mathematica, 1930