English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  From Graphs to Manifolds: Weak and Strong Pointwise Consistency of Graph Laplacians

Hein, M., Audibert, J., & von Luxburg, U. (2005). From Graphs to Manifolds: Weak and Strong Pointwise Consistency of Graph Laplacians. In P. Auer, & R. Meir (Eds.), Learning Theory: 18th Annual Conference on Learning Theory, COLT 2005, Bertinoro, Italy, June 27-30, 2005 (pp. 470-485). Berlin, Germany: Springer.

Item is

Files

show Files

Locators

show
hide
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Hein, M1, 2, Author           
Audibert, J, Author
von Luxburg, U, 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: In the machine learning community it is generally believed that graph Laplacians corresponding to a finite sample of data points
converge to a continuous Laplace operator if the sample size
increases. Even though this assertion serves as a justification for many
Laplacian-based algorithms, so far only some aspects of this claim
have been rigorously proved. In this paper we close this gap by
establishing the strong pointwise consistency of a family of
graph Laplacians with data-dependent weights to some
weighted Laplace operator. Our investigation also
includes the important case where the data lies on a submanifold of
R^d.

Details

show
hide
Language(s):
 Dates: 2005-06
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 3213
 Degree: -

Event

show
hide
Title: 18th Annual Conference on Learning Theory (COLT 2005)
Place of Event: Bertinoro, Italy
Start-/End Date: 2005-06-27 - 2005-06-30

Legal Case

show

Project information

show

Source 1

show
hide
Title: Learning Theory: 18th Annual Conference on Learning Theory, COLT 2005, Bertinoro, Italy, June 27-30, 2005
Source Genre: Proceedings
 Creator(s):
Auer, P, Editor
Meir, R, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 470 - 485 Identifier: ISBN: 978-3-540-26556-6

Source 2

show
hide
Title: Lecture Notes in Computer Scienc
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 3559 Sequence Number: - Start / End Page: - Identifier: -