A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation
arXiv:1810.01545
Abstract
In the problem of domain adaptation for binary classification, the learner is presented with labeled examples from a source domain, and must correctly classify unlabeled examples from a target domain, which may differ from the source. Previous work on this problem has assumed that the performance measure of interest is the expected value of some loss function. We introduce a new Neyman-Pearson-like criterion and argue that, for this optimality criterion, stronger domain adaptation results are possible than what has previously been established. In particular, we study a class of domain adaptation problems that generalizes both the covariate shift assumption and a model for feature-dependent label noise, and establish optimal classification on the target domain despite not having access to labelled data from this domain.
arXiv commentALT 2019
References in corpus (9)
- Domain Adaptation: Learning Bounds and Algorithms
- Fast learning rates for plug-in classifiers
- Making Risk Minimization Tolerant to Label Noise
- Neyman-Pearson (NP) classification algorithms and NP receiver operating characteristics (NP-ROC)
- Analysis of Kernel Mean Matching under Covariate Shift
- A New PAC-Bayesian Perspective on Domain Adaptation
- Learning with Bounded Instance- and Label-dependent Label Noise
- Intentional Control of Type I Error over Unconscious Data Distortion: a Neyman-Pearson Approach to Text Classification
- A plug-in approach to maximising precision at the top and recall at the top