English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Statistical Performance of Support Vector Machines

Blanchard, G., Bousquet, O., & Massart, P. (2004). Statistical Performance of Support Vector Machines. The Annals of Statistics, 36(2), 489-531. doi:10.1214/009053607000000839.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-F3BD-4 Version Permalink: http://hdl.handle.net/21.11116/0000-0005-4F56-3
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Blanchard, G1, Author              
Bousquet, O1, Author              
Massart, P, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: The support vector machine (SVM) algorithm is well known to the computer learning community for its very good practical results. The goal of the present paper is to study this algorithm from a statistical perspective, using tools of concentration theory and empirical processes. Our main result builds on the observation made by other authors that the SVM can be viewed as a statistical regularization procedure. From this point of view, it can also be interpreted as a model selection principle using a penalized criterion. It is then possible to adapt general methods related to model selection in this framework to study two important points: (1) what is the minimum penalty and how does it compare to the penalty actually used in the SVM algorithm; (2) is it possible to obtain “oracle inequalities” in that setting, for the specific loss function used in the SVM algorithm? We show that the answer to the latter question is positive and provides relevant insight to the former. Our result shows that it is possible to obtain fast rates of convergence for SVMs.

Details

show
hide
Language(s):
 Dates: 2004-04
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: 2731
DOI: 10.1214/009053607000000839
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: The Annals of Statistics
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cleveland, Ohio [etc] : Institute of Mathematical Statistics [etc.]
Pages: - Volume / Issue: 36 (2) Sequence Number: - Start / End Page: 489 - 531 Identifier: ISSN: 0090-5364
CoNE: https://pure.mpg.de/cone/journals/resource/954925461135