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

Masanori Kawakita, Junichi Takeuchi

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語英語
ホスト出版物のタイトル33rd International Conference on Machine Learning, ICML 2016
編集者Kilian Q. Weinberger, Maria Florina Balcan
出版社International Machine Learning Society (IMLS)
ページ2896-2905
ページ数10
ISBN(電子版)9781510829008
出版ステータス出版済み - 2016
イベント33rd International Conference on Machine Learning, ICML 2016 - New York City, 米国
継続期間: 6 19 20166 24 2016

出版物シリーズ

名前33rd International Conference on Machine Learning, ICML 2016
4

その他

その他33rd International Conference on Machine Learning, ICML 2016
国/地域米国
CityNew York City
Period6/19/166/24/16

All Science Journal Classification (ASJC) codes

  • 人工知能
  • ソフトウェア
  • コンピュータ ネットワークおよび通信

フィンガープリント

「Barron and cover's theory in supervised learning and its application to lasso」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル