Local Rademacher Complexities

Bartlett, P; Bousquet, O; Mendelson, S

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

学術論文

Local Rademacher Complexities

MPS-Authors

/persons/resource/persons83824

Bousquet, O
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

https://projecteuclid.org/download/pdfview_1/euclid.aos/1123250221
(出版社版)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

公開されているフルテキストはありません

付随資料 (公開)

There is no public supplementary material available

引用

Bartlett, P., Bousquet, O., & Mendelson, S. (2005). Local Rademacher Complexities. The Annals of Statistics, 33(4), 1497-1537.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-D4A3-9

要旨

We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical version of Rademacher averages, in the sense that the Rademacher averages are computed from the data, on a subset of functions with small empirical error. We present some applications to classification and prediction with convex function classes, and with kernel classes in particular.