de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Book Chapter

Projected Newton-type methods in machine learning

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons76055

Schmidt,  M.
Dept. Metastable and Low-Dimensional Materials, Max Planck Institute for Intelligent Systems, Max Planck Society;
Dept. Modern Magnetic Systems, Max Planck Institute for Intelligent Systems, Max Planck Society;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons76142

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

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

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


Cite as: http://hdl.handle.net/11858/00-001M-0000-0010-4BF4-B
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.