Barron and cover's theory in supervised learning and its application to lasso

Masanori Kawakita, Junnichi Takeuchi

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

1 Citation (Scopus)

Abstract

We study Barron and Cover's theory (BC theory) in supervised learning. The original BC theory can be applied to supervised learning only approximately and limitedly. Though Barron & Luo (2008) and Chatteijee & Barron (2014a) succeeded in removing the approximation, their idea cannot be essentially applied to supervised learning in general. By solving this issue, we propose an extension of BC theory to supervised learning. The extended theory has several advantages inherited from the original BC theory. First, it holds for finite sample number n. Second, it requires remarkably few assumptions. Third, it gives a justification of the MDL principle in supervised learning. We also derive new risk and regret bounds of lasso with random design as its application. The derived risk bound hold for any finite n without bound-edness of features in contrast to past work. Behavior of the regret bound is investigated by numerical simulations. We believe that this is the first extension of BC theory to general supervised learning without approximation.

Original languageEnglish
Title of host publication33rd International Conference on Machine Learning, ICML 2016
PublisherInternational Machine Learning Society (IMLS)
Pages2896-2905
Number of pages10
Volume4
ISBN (Electronic)9781510829008
Publication statusPublished - 2016
Event33rd International Conference on Machine Learning, ICML 2016 - New York City, United States
Duration: Jun 19 2016Jun 24 2016

Other

Other33rd International Conference on Machine Learning, ICML 2016
CountryUnited States
CityNew York City
Period6/19/166/24/16

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Barron and cover's theory in supervised learning and its application to lasso'. Together they form a unique fingerprint.

Cite this