Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders

Eleni Sgouritsa, Dominik Janzing, Jonas Peters, Bernhard Schölkopf
Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, PMLR R11:628-637, 2013.

Abstract

We propose a kernel method to identify finite mixtures of nonparametric product distributions. It is based on a Hilbert space embedding of the joint distribution. The rank of the constructed tensor is equal to the number of mixture components. We present an algorithm to recover the components by partitioning the data points into clusters such that the variables are jointly conditionally in-dependent given the cluster. This method can be used to identify finite confounders.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR11-sgouritsa13a, title = {Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders}, author = {Sgouritsa, Eleni and Janzing, Dominik and Peters, Jonas and Sch{\"o}lkopf, Bernhard}, booktitle = {Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence}, pages = {628--637}, year = {2013}, editor = {Nicholson, Ann and Smyth, Padhraic}, volume = {R11}, series = {Proceedings of Machine Learning Research}, month = {12--14 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r11/main/assets/sgouritsa13a/sgouritsa13a.pdf}, url = {https://proceedings.mlr.press/r11/sgouritsa13a.html}, abstract = {We propose a kernel method to identify finite mixtures of nonparametric product distributions. It is based on a Hilbert space embedding of the joint distribution. The rank of the constructed tensor is equal to the number of mixture components. We present an algorithm to recover the components by partitioning the data points into clusters such that the variables are jointly conditionally in-dependent given the cluster. This method can be used to identify finite confounders.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders %A Eleni Sgouritsa %A Dominik Janzing %A Jonas Peters %A Bernhard Schölkopf %B Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2013 %E Ann Nicholson %E Padhraic Smyth %F pmlr-vR11-sgouritsa13a %I PMLR %P 628--637 %U https://proceedings.mlr.press/r11/sgouritsa13a.html %V R11 %X We propose a kernel method to identify finite mixtures of nonparametric product distributions. It is based on a Hilbert space embedding of the joint distribution. The rank of the constructed tensor is equal to the number of mixture components. We present an algorithm to recover the components by partitioning the data points into clusters such that the variables are jointly conditionally in-dependent given the cluster. This method can be used to identify finite confounders. %Z Reissued by PMLR on 04 October 2026.
APA
Sgouritsa, E., Janzing, D., Peters, J. & Schölkopf, B.. (2013). Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders. Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R11:628-637 Available from https://proceedings.mlr.press/r11/sgouritsa13a.html. Reissued by PMLR on 04 October 2026.

Related Material