From Statistical to Causal Learning
Artificial Intelligence
2022-04-04 v1 Machine Learning
Machine Learning
Abstract
We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality. Some of the hard open problems of machine learning and AI are intrinsically related to causality, and progress may require advances in our understanding of how to model and infer causality from data.
Cite
@article{arxiv.2204.00607,
title = {From Statistical to Causal Learning},
author = {Bernhard Schölkopf and Julius von Kügelgen},
journal= {arXiv preprint arXiv:2204.00607},
year = {2022}
}
Comments
To appear in the Proceedings of the International Congress of Mathematicians 2022, EMS Press. Both authors contributed equally to this work; names are listed in alphabetical order. 34 pages (28 content pages + references), 12 figures, 2 tables. arXiv admin note: text overlap with arXiv:1911.10500