English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Asymptotic Properties of the Fisher Kernel

Tsuda, K., Akaho, S., Kawanabe, M., & Müller, K. (2004). Asymptotic Properties of the Fisher Kernel. Neural computation, 16(1), 115-137. doi:10.1162/08997660460734029.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0013-DA51-B Version Permalink: http://hdl.handle.net/21.11116/0000-0005-4F8E-4
Genre: Journal Article

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Tsuda, K1, 2, Author              
Akaho, S, Author
Kawanabe, M, Author
Müller, KR, 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, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: This letter analyzes the Fisher kernel from a statistical point of view. The Fisher kernel is a particularly interesting method for constructing a model of the posterior probability that makes intelligent use of unlabeled data (i.e., of the underlying data density). It is important to analyze and ultimately understand the statistical properties of the Fisher kernel. To this end, we first establish sufficient conditions that the constructed posterior model is realizable (i.e., it contains the true distribution). Realizability immediately leads to consistency results. Subsequently, we focus on an asymptotic analysis of the generalization error, which elucidates the learning curves of the Fisher kernel and how unlabeled data contribute to learning. We also point out that the squared or log loss is theoretically preferable-because both yield consistent estimators-to other losses such as the exponential loss, when a linear classifier is used together with the Fisher kernel. Therefore, this letter underlines that the Fisher kernel should be viewed not as a heuristics but as a powerful statistical tool with well-controlled statistical properties.

Details

show
hide
Language(s):
 Dates: 2004-01
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: 2268
DOI: 10.1162/08997660460734029
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Neural computation
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, Mass. : MIT Press
Pages: - Volume / Issue: 16 (1) Sequence Number: - Start / End Page: 115 - 137 Identifier: ISSN: 0899-7667
CoNE: https://pure.mpg.de/cone/journals/resource/954925561591