Header logo is ei

On Causal Discovery with Cyclic Additive Noise Models

2011

Conference Paper

ei


We study a particular class of cyclic causal models, where each variable is a (possibly nonlinear) function of its parents and additive noise. We prove that the causal graph of such models is generically identifiable in the bivariate, Gaussian-noise case. We also propose a method to learn such models from observational data. In the acyclic case, the method reduces to ordinary regression, but in the more challenging cyclic case, an additional term arises in the loss function, which makes it a special case of nonlinear independent component analysis. We illustrate the proposed method on synthetic data.

Author(s): Mooij, J. and Janzing, D. and Schölkopf, B. and Heskes, T.
Book Title: Advances in Neural Information Processing Systems 24
Pages: 639-647
Year: 2011
Day: 0
Editors: J Shawe-Taylor and RS Zemel and PL Bartlett and FCN Pereira and KQ Weinberger
Publisher: Curran Associates, Inc.

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Address: Red Hook, NY, USA
Digital: 0
Event Name: Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011)
Event Place: Granada, Spain

Links: PDF
Web

BibTex

@inproceedings{MooijJSH2012,
  title = {On Causal Discovery with Cyclic Additive Noise Models},
  author = {Mooij, J. and Janzing, D. and Sch{\"o}lkopf, B. and Heskes, T.},
  booktitle = {Advances in Neural Information Processing Systems 24},
  pages = {639-647},
  editors = {J Shawe-Taylor and RS Zemel and PL Bartlett and FCN Pereira and KQ Weinberger},
  publisher = {Curran Associates, Inc.},
  address = {Red Hook, NY, USA},
  year = {2011}
}