Generalization Bounds via Eigenvalues of the Gram matrix

Schölkopf, B; Shawe-Taylor, J; Smola, AJ; Williamson, RC

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

報告書

Generalization Bounds via Eigenvalues of the Gram matrix

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.349
(全文テキスト（全般）)

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

Schölkopf, B., Shawe-Taylor, J., Smola, A., & Williamson, R.(1999). Generalization Bounds via Eigenvalues of the Gram matrix (NC2-TR-1999-035). London, UK: University of London: Royal Holloway College: NeuroCOLT 2.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-E77D-4

要旨

Model selection in Support Vector machines is usually carried out by minimizing the quotient of the radius of the smallest enclosing sphere of the data and the observed margin on the training set. We provide a new criterion taking the distribution within that sphere into account by considering the Gram matrix of the data. In particular, this makes use of the eigenvalue distribution of the matrix. Experimental results on real world data show that this new criterion provides a good prediction of the shape of the curve relating generalization error to kernel width.