English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Quasi-Newton Methods: A New Direction

Hennig, P., & Kiefel, M. (2012). Quasi-Newton Methods: A New Direction. In J. Langford, & J. Pineau (Eds.), 29th International Conference on Machine Learning (ICML 2012) (pp. 25-32). Madison, WI, USA: International Machine Learning Society.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-B6CA-1 Version Permalink: https://hdl.handle.net/21.11116/0000-0001-1BAF-D
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://icml.cc/2012/papers/25.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Hennig, P1, Author           
Kiefel, M1, Author           
Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, DE, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: Four decades after their invention, quasi- Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that t a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more ecient use of available information at computational cost similar to its predecessors.

Details

show
hide
Language(s):
 Dates: 2012-07
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: HennigK2012
 Degree: -

Event

show
hide
Title: 29th International Conference on Machine Learning (ICML 2012)
Place of Event: Edinburgh, UK
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: 29th International Conference on Machine Learning (ICML 2012)
Source Genre: Proceedings
 Creator(s):
Langford, J, Editor
Pineau, J, Editor
Affiliations:
-
Publ. Info: Madison, WI, USA : International Machine Learning Society
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 25 - 32 Identifier: ISBN: 978-1-4503-1285-1