English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Nonlinear directed acyclic structure learning with weakly additive noise models

Tillman, R., Gretton, A., & Spirtes, P. (2010). Nonlinear directed acyclic structure learning with weakly additive noise models. In Y. Bengio, D. Schuurmans, C. Williams, & A. Culotta (Eds.), Advances in Neural Information Processing Systems 22 (pp. 1847-1855). Red Hook, NY, USA: Curran.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C0CE-C Version Permalink: https://hdl.handle.net/21.11116/0000-0004-D2DC-7
Genre: Conference Paper

Files

show Files

Creators

show
hide
 Creators:
Tillman, RE, Author
Gretton, A1, 2, Author           
Spirtes, P, 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 recently proposed emphadditive noise model has advantages over previous structure learning algorithms, when attempting to recover some true data generating mechanism, since it (i) does not assume linearity or Gaussianity and (ii) can recover a unique DAG rather than an equivalence class. However, its original extension to the multivariate case required enumerating all possible DAGs, and for some special distributions, e.g. linear Gaussian, the model is invertible and thus cannot be used for structure learning. We present a new approach which combines a PC style search using recent advances in kernel measures of conditional dependence with local searches for additive noise models in substructures of the equivalence class. This results in a more computationally efficient approach that is useful for arbitrary distributions even when additive noise models are invertible. Experiments with synthetic and real data show that this method is more accurate than previous methods when data are nonlinear and/or non-Gaussian.

Details

show
hide
Language(s):
 Dates: 2010-04
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: BibTex Citekey: 6133
 Degree: -

Event

show
hide
Title: 23rd Annual Conference on Neural Information Processing Systems (NIPS 2009)
Place of Event: Vancouver, BC, Canada
Start-/End Date: 2009-12-07 - 2009-12-10

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 22
Source Genre: Proceedings
 Creator(s):
Bengio, Y, Editor
Schuurmans, D, Editor
Lafferty, J, Painter
Williams, C, Editor
Culotta, A, Editor
Affiliations:
-
Publ. Info: Red Hook, NY, USA : Curran
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1847 - 1855 Identifier: ISBN: 978-1-615-67911-9