Скачать с ютуб Jonas Peters: Causality and Distribution Generalization в хорошем качестве

Jonas Peters: Causality and Distribution Generalization

"Causality and Distribution Generalization" Jonas Peters, University of Copenhagen Discussant: Yuansi Chen, ETH Zürich Abstract: Purely predictive methods do not perform well when the test distribution changes too much from the training distribution. Causal models are known to be stable with respect to distributional shifts such as arbitrarily strong interventions on the covariates, but may not perform well when the test distribution differs only mildly from the training distribution. As a result, methods have been proposed that provide a trade off between causal and predictive models. We provide conditions under which such methods can be proved to generalize well to unseen distributions discuss theoretical limitations of this idea and show an example for inferring metabolic networks. arXiv:2006.07433 June 16, 2020