Hierarchical Label Queries with Data-Dependent Partitions
Samory Kpotufe, Ruth Urner, Shai Ben-David · MPG.PuRe (Max Planck Society) · 2015
Given a joint distributionPX;Y over a spaceX and a label setY =f0; 1g, we consider the problem of recovering the labels of an unlabeled sample with as few label queries as possible. The recovered labels can be passed to a passive learner, thus turning the procedure into an active learning approach. We analyze a family of labeling procedures based on a hierarchical clustering of the data. While such labeling procedures have been studied in the past, we provide a new parametrization ofPX;Y that captures their behavior in general low-noise settings, and which accounts for data-dependent clustering, thus providing new theoretical underpinning to practically used tools.