Help Privacy Policy Disclaimer
  Advanced SearchBrowse




Book Chapter

Projected Newton-type methods in machine learning


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

Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available

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.

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