Trading Convexity for Scalability

Collobert, R; Sinz, F; Weston, J; Bottou, L; Bottou,; L.,; Chapelle, O.; DeCoste, D.; Weston, J.

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

このアイテムの新しいバージョンが利用可能です:
https://pure.mpg.de/pubman/item/item_1790268_3

詳細要約

公開

書籍の一部

Trading Convexity for Scalability

MPS-Authors

/persons/resource/persons84226

Sinz, F
Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84311

Weston, J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource

There are no locators available

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

Collobert, R., Sinz, F., Weston, J., & Bottou, L. (2007). Trading Convexity for Scalability. In Large Scale Kernel Machines (pp. 275-300). Cambridge, MA, USA: MIT Press.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-CC09-2

要旨

Convex learning algorithms, such as Support Vector Machines (SVMs), are often seen as highly desirable because they offer strong practical properties and are amenable to theoretical analysis. However, in this work we show how nonconvexity can provide scalability advantages over convexity. We show how concave-convex programming can be applied to produce (i) faster SVMs where training errors are no longer support vectors, and (ii) much faster Transductive SVMs.