A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation

2018/10/03 by Clayton Scott, Scott, Clayton · 2 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.1810.01545

openalex publication_date 2018/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Domain Adaptation: Learning Bounds and Algorithms
• Sample Selection Bias as a Specification Error
• Classification with Asymmetric Label Noise: Consistency and Maximal\n Denoising

Cited by

• Domain Generalization Under Posterior Drift
• Fairness Evaluation in Presence of Biased Noisy Labels

Related

• An introduction to domain adaptation and transfer learning
• A survey on domain adaptation theory: learning bounds and theoretical guarantees
• Algorithms and Theory for Supervised Gradual Domain Adaptation
• On Learning Invariant Representation for Domain Adaptation
• Bridging Theory and Algorithm for Domain Adaptation