Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

Paul Rolland, Volkan Cevher, Matthäus Kleindessner, Chris Russell, Dominik Janzing, Bernhard Schölkopf, Francesco Locatello
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:18741-18753, 2022.

Abstract

This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal discovery methods. To showcase our approach, we also propose a new efficient method for approximating the score’s Jacobian, enabling to recover the causal graph. Empirically, we find that the new algorithm, called SCORE, is competitive with state-of-the-art causal discovery methods while being significantly faster.

Cite this Paper


BibTeX
@InProceedings{pmlr-v162-rolland22a, title = {Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models}, author = {Rolland, Paul and Cevher, Volkan and Kleindessner, Matth{\"a}us and Russell, Chris and Janzing, Dominik and Sch{\"o}lkopf, Bernhard and Locatello, Francesco}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {18741--18753}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/rolland22a/rolland22a.pdf}, url = {https://proceedings.mlr.press/v162/rolland22a.html}, abstract = {This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal discovery methods. To showcase our approach, we also propose a new efficient method for approximating the score’s Jacobian, enabling to recover the causal graph. Empirically, we find that the new algorithm, called SCORE, is competitive with state-of-the-art causal discovery methods while being significantly faster.} }
Endnote
%0 Conference Paper %T Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models %A Paul Rolland %A Volkan Cevher %A Matthäus Kleindessner %A Chris Russell %A Dominik Janzing %A Bernhard Schölkopf %A Francesco Locatello %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-rolland22a %I PMLR %P 18741--18753 %U https://proceedings.mlr.press/v162/rolland22a.html %V 162 %X This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models. Using score matching algorithms as a building block, we show how to design a new generation of scalable causal discovery methods. To showcase our approach, we also propose a new efficient method for approximating the score’s Jacobian, enabling to recover the causal graph. Empirically, we find that the new algorithm, called SCORE, is competitive with state-of-the-art causal discovery methods while being significantly faster.
APA
Rolland, P., Cevher, V., Kleindessner, M., Russell, C., Janzing, D., Schölkopf, B. & Locatello, F.. (2022). Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:18741-18753 Available from https://proceedings.mlr.press/v162/rolland22a.html.

Related Material