Adaptation algorithm and theory based on generalized discrepancy

Corinna Cortes, Mehryar Mohri, Andrés Muñoz Medina

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a new algorithm for domain adaptation improving upon the discrepancy minimization algorithm (DM), which was previously shown to outperform a number of popular algorithms designed for this task. Unlike most previous approaches adopted for domain adaptation, our algorithm does not consist of a fixed reweighting of the losses over the training sample. Instead, it uses a reweighting that depends on the hypothesis considered and is based on the minimization of a new measure of generalized discrepancy. We give a detailed description of our algorithm and show that it can be formulated as a convex optimization problem. We also present a detailed theoretical analysis of its learning guarantees, which helps us select its parameters. Finally, we report the results of experiments demonstrating that it improves upon the DM algorithm in several tasks.

Original languageEnglish (US)
Title of host publicationKDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages169-178
Number of pages10
ISBN (Electronic)9781450336642
DOIs
StatePublished - Aug 10 2015
Event21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015 - Sydney, Australia
Duration: Aug 10 2015Aug 13 2015

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Volume2015-August

Other

Other21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2015
CountryAustralia
CitySydney
Period8/10/158/13/15

ASJC Scopus subject areas

  • Software
  • Information Systems

Fingerprint Dive into the research topics of 'Adaptation algorithm and theory based on generalized discrepancy'. Together they form a unique fingerprint.

  • Cite this

    Cortes, C., Mohri, M., & Medina, A. M. (2015). Adaptation algorithm and theory based on generalized discrepancy. In KDD 2015 - Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 169-178). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Vol. 2015-August). Association for Computing Machinery. https://doi.org/10.1145/2783258.2783368