Hierarchical label queries with data-dependent partitions

Samory Kpotufe, Ruth Urner, Shai Ben-David

Research output: Contribution to journalConference article

Abstract

Given a joint distribution PX;Y over a space X and a label set Y = (0; 1), 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 of PX;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.

Original languageEnglish (US)
JournalJournal of Machine Learning Research
Volume40
Issue number2015
StatePublished - Jan 1 2015
Event28th Conference on Learning Theory, COLT 2015 - Paris, France
Duration: Jul 2 2015Jul 6 2015

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Hierarchical label queries with data-dependent partitions'. Together they form a unique fingerprint.

  • Cite this

    Kpotufe, S., Urner, R., & Ben-David, S. (2015). Hierarchical label queries with data-dependent partitions. Journal of Machine Learning Research, 40(2015).