English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Uniform Convergence of Adaptive Graph-Based Regularization

Hein, M. (2006). Uniform Convergence of Adaptive Graph-Based Regularization. In G. Lugosi, & H. Simon (Eds.), Learning Theory: 19th Annual Conference on Learning Theory, COLT 2006, Pittsburgh, PA, USA, June 22-25, 2006 (pp. 50-64). Berlin, Germany: Springer.

Item is

Files

show Files

Locators

show
hide
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Hein, M1, 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: The regularization functional induced by the graph Laplacian of a random
neighborhood graph based on the data is adaptive in two ways. First it adapts to an underlying
manifold structure and second to the density of the data-generating probability measure.
We identify in this paper the limit of the regularizer and show
uniform convergence over the space of Hoelder functions. As an intermediate
step we derive upper bounds on the covering numbers of Hoelder functions on
compact Riemannian manifolds, which are of independent interest
for the theoretical analysis of manifold-based learning methods.

Details

show
hide
Language(s):
 Dates: 2006-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/11776420_7
BibTex Citekey: 3893
 Degree: -

Event

show
hide
Title: 19th Annual Conference on Learning Theory (COLT 2006)
Place of Event: Pittsburgh, PA, USA
Start-/End Date: 2006-06-22 - 2006-06-25

Legal Case

show

Project information

show

Source 1

show
hide
Title: Learning Theory: 19th Annual Conference on Learning Theory, COLT 2006, Pittsburgh, PA, USA, June 22-25, 2006
Source Genre: Proceedings
 Creator(s):
Lugosi, G, Editor
Simon, HU, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 50 - 64 Identifier: ISBN: 978-3-540-35294-5