English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Projected Newton-type methods in machine learning

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.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-B8DE-7 Version Permalink: http://hdl.handle.net/21.11116/0000-0001-AB1E-E
Genre: Book Chapter

Files

show Files

Creators

show
hide
 Creators:
Schmidt, M, Author
Kim, D, Author
Sra, S.1, Author              
Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: 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.

Details

show
hide
Language(s):
 Dates: 2011-12
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 6824
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Optimization for Machine Learning
Source Genre: Book
 Creator(s):
Sra, S1, Editor            
Nowozin, S1, Editor            
Wright, SJ, Editor
Affiliations:
1 Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795            
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 305 - 330 Identifier: ISBN: 978-0-262-01646-9

Source 2

show
hide
Title: Neural information processing series
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: -