English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Concentration Inequalities and Empirical Processes Theory Applied to the Analysis of Learning Algorithms

Bousquet, O. (2002). Concentration Inequalities and Empirical Processes Theory Applied to the Analysis of Learning Algorithms. PhD Thesis, École Polytechnique: Department of Applied Mathematics, Paris, France.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-E143-7 Version Permalink: http://hdl.handle.net/21.11116/0000-0005-9E3D-6
Genre: Thesis

Files

show Files

Creators

show
hide
 Creators:
Bousquet, O1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: New classification algorithms based on the notion of 'margin' (e.g. Support Vector Machines, Boosting) have recently been developed. The goal of this thesis is to better understand how they work, via a study of their theoretical performance. In order to do this, a general framework for real-valued classification is proposed. In this framework, it appears that the natural tools to use are Concentration Inequalities and Empirical Processes Theory. Thanks to an adaptation of these tools, a new measure of the size of a class of functions is introduced, which can be computed from the data. This allows, on the one hand, to better understand the role of eigenvalues of the kernel matrix in Support Vector Machines, and on the other hand, to obtain empirical model selection criteria.

Details

show
hide
Language(s):
 Dates: 2002-11
 Publication Status: Published in print
 Pages: 235
 Publishing info: Paris, France : École Polytechnique: Department of Applied Mathematics
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 1444
 Degree: PhD

Event

show

Legal Case

show

Project information

show

Source

show