Private Causal Inference

Matt J. Kusner, Yu Sun, Karthik Sridharan, Kilian Q. Weinberger
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:1308-1317, 2016.

Abstract

Causal inference deals with identifying which random variables ”cause” or control other random variables. Recent advances on the topic of causal inference based on tools from statistical estimation and machine learning have resulted in practical algorithms for causal inference. Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few. However, these promising applications for causal inference are often ones that involve sensitive or personal data of users that need to be kept private (e.g., medical records, personal finances, etc). Therefore, there is a need for the development of causal inference methods that preserve data privacy. We study the problem of inferring causality using the current, popular causal inference framework, the additive noise model (ANM) while simultaneously ensuring privacy of the users. Our framework provides differential privacy guarantees for a variety of ANM variants. We run extensive experiments, and demonstrate that our techniques are practical and easy to implement.

Cite this Paper

BibTeX
@InProceedings{pmlr-v51-kusner16, title = {Private Causal Inference}, author = {Kusner, Matt J. and Sun, Yu and Sridharan, Karthik and Weinberger, Kilian Q.}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics}, pages = {1308--1317}, year = {2016}, editor = {Gretton, Arthur and Robert, Christian C.}, volume = {51}, series = {Proceedings of Machine Learning Research}, address = {Cadiz, Spain}, month = {09--11 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v51/kusner16.pdf}, url = {https://proceedings.mlr.press/v51/kusner16.html}, abstract = {Causal inference deals with identifying which random variables ”cause” or control other random variables. Recent advances on the topic of causal inference based on tools from statistical estimation and machine learning have resulted in practical algorithms for causal inference. Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few. However, these promising applications for causal inference are often ones that involve sensitive or personal data of users that need to be kept private (e.g., medical records, personal finances, etc). Therefore, there is a need for the development of causal inference methods that preserve data privacy. We study the problem of inferring causality using the current, popular causal inference framework, the additive noise model (ANM) while simultaneously ensuring privacy of the users. Our framework provides differential privacy guarantees for a variety of ANM variants. We run extensive experiments, and demonstrate that our techniques are practical and easy to implement.} }
Endnote
%0 Conference Paper %T Private Causal Inference %A Matt J. Kusner %A Yu Sun %A Karthik Sridharan %A Kilian Q. Weinberger %B Proceedings of the 19th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2016 %E Arthur Gretton %E Christian C. Robert %F pmlr-v51-kusner16 %I PMLR %P 1308--1317 %U https://proceedings.mlr.press/v51/kusner16.html %V 51 %X Causal inference deals with identifying which random variables ”cause” or control other random variables. Recent advances on the topic of causal inference based on tools from statistical estimation and machine learning have resulted in practical algorithms for causal inference. Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few. However, these promising applications for causal inference are often ones that involve sensitive or personal data of users that need to be kept private (e.g., medical records, personal finances, etc). Therefore, there is a need for the development of causal inference methods that preserve data privacy. We study the problem of inferring causality using the current, popular causal inference framework, the additive noise model (ANM) while simultaneously ensuring privacy of the users. Our framework provides differential privacy guarantees for a variety of ANM variants. We run extensive experiments, and demonstrate that our techniques are practical and easy to implement.
RIS
TY - CPAPER TI - Private Causal Inference AU - Matt J. Kusner AU - Yu Sun AU - Karthik Sridharan AU - Kilian Q. Weinberger BT - Proceedings of the 19th International Conference on Artificial Intelligence and Statistics DA - 2016/05/02 ED - Arthur Gretton ED - Christian C. Robert ID - pmlr-v51-kusner16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 51 SP - 1308 EP - 1317 L1 - http://proceedings.mlr.press/v51/kusner16.pdf UR - https://proceedings.mlr.press/v51/kusner16.html AB - Causal inference deals with identifying which random variables ”cause” or control other random variables. Recent advances on the topic of causal inference based on tools from statistical estimation and machine learning have resulted in practical algorithms for causal inference. Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few. However, these promising applications for causal inference are often ones that involve sensitive or personal data of users that need to be kept private (e.g., medical records, personal finances, etc). Therefore, there is a need for the development of causal inference methods that preserve data privacy. We study the problem of inferring causality using the current, popular causal inference framework, the additive noise model (ANM) while simultaneously ensuring privacy of the users. Our framework provides differential privacy guarantees for a variety of ANM variants. We run extensive experiments, and demonstrate that our techniques are practical and easy to implement. ER -
APA
Kusner, M.J., Sun, Y., Sridharan, K. & Weinberger, K.Q.. (2016). Private Causal Inference. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 51:1308-1317 Available from https://proceedings.mlr.press/v51/kusner16.html.

Related Material