Projected Newton-type methods in machine learning

Schmidt, M; Kim, D; Sra, 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

書籍の一部

Projected Newton-type methods in machine learning

MPS-Authors

/persons/resource/persons76142

Sra, S.
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

External Resource

https://doc.lagout.org/science/Artificial%20Intelligence/Machine%20learning/Optimization%20for%20Machine%20Learning%20%5BSra%2C%20Nowozin%20%26%20Wright%202011-09-30%5D.pdf
(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

Schmidt, M., Kim, D., & Sra, S. (2011). Projected Newton-type methods in machine learning. In S., Sra, S., Nowozin, & S., Wright (Eds.), Optimization for Machine Learning (pp. 305-330). Cambridge, MA, USA: MIT Press.

引用: https://hdl.handle.net/11858/00-001M-0000-0013-B8DE-7

要旨

We consider projected Newton-type methods for solving large-scale optimization problems arising in machine learning and related fields. We first introduce an algorithmic framework for projected Newton-type methods by reviewing a canonical projected (quasi-)Newton method. This method, while conceptually pleasing, has a high computation cost per iteration. Thus, we discuss two variants that are more scalable, namely, two-metric projection and inexact projection methods. Finally, we show how to apply the Newton-type framework to handle non-smooth objectives. Examples are provided throughout the chapter to illustrate machine learning applications of our framework.