Department of Mathematical Sciences
|DATE:||Thursday, April 22, 2021|
|TIME:||1:15pm – 2:15pm|
|SPEAKER:||Baozhen Wang, Binghamton University|
|TITLE:||A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation|
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. The author 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.