A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation
This addresses the problem of adapting classifiers across domains for researchers and practitioners, but it appears incremental as it builds on existing assumptions like covariate shift.
The paper tackles domain adaptation for binary classification by introducing a new Neyman-Pearson-like criterion, showing that stronger adaptation results are possible than with previous loss-based approaches, and establishes optimal classification on the target domain without labeled data from it.
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.