%0 Journal Article %1 subbaswamy2018preventing %A Subbaswamy, Adarsh %A Schulam, Peter %A Saria, Suchi %D 2018 %K causal-analysis invariance %T Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport %U http://arxiv.org/abs/1812.04597 %X Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in the training domain that will generalize to the target domain by incorporating prior knowledge of aspects of the data generating process that are expected to differ as expressed in a causal selection diagram. Specifically, we remove variables generated by unstable mechanisms from the joint factorization to yield the Surgery Estimator---an interventional distribution that is invariant to the differences across environments. We prove that the surgery estimator finds stable relationships in strictly more scenarios than previous approaches which only consider conditional relationships, and demonstrate this in simulated experiments. We also evaluate on real world data for which the true causal diagram is unknown, performing competitively against entirely data-driven approaches.

@article{subbaswamy2018preventing, abstract = {Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in the training domain that will generalize to the target domain by incorporating prior knowledge of aspects of the data generating process that are expected to differ as expressed in a causal selection diagram. Specifically, we remove variables generated by unstable mechanisms from the joint factorization to yield the Surgery Estimator---an interventional distribution that is invariant to the differences across environments. We prove that the surgery estimator finds stable relationships in strictly more scenarios than previous approaches which only consider conditional relationships, and demonstrate this in simulated experiments. We also evaluate on real world data for which the true causal diagram is unknown, performing competitively against entirely data-driven approaches.}, added-at = {2019-08-06T11:37:13.000+0200}, author = {Subbaswamy, Adarsh and Schulam, Peter and Saria, Suchi}, biburl = {https://www.bibsonomy.org/bibtex/28d1ba8d2aac1d0182d7305b50f17ff7f/kirk86}, description = {[1812.04597] Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport}, interhash = {f9d1da2538555d5c534c8792249370b7}, intrahash = {8d1ba8d2aac1d0182d7305b50f17ff7f}, keywords = {causal-analysis invariance}, note = {cite arxiv:1812.04597Comment: In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. Previously presented at the NeurIPS 2018 Causal Learning Workshop}, timestamp = {2019-08-06T11:37:13.000+0200}, title = {Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport}, url = {http://arxiv.org/abs/1812.04597}, year = 2018 }