TBD.

Léon Bottou, From Causal Graphs to Causal Invariance

For many problems, it’s difficult to even attempt drawing a causal graph. While structural causal models provide a complete framework for causal inference, it is often hard to encode known physical laws (such as Newton’s gravitation, or the ideal gas law) as causal graphs. In familiar machine learning territory, how does one model the causal relationships between individual pixels and a target prediction? This is one of the motivating questions behind the paper Invariant Risk Minimization (IRM). In place of structured graphs, the authors elevate invariance to the defining feature of causality.

Nisha Muktewar and Chris Wallace Causality for Machine Learning is the book Bottou recommends on this theme.

## References

*Advances in Neural Information Processing Systems 29*, edited by D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett, 2946–54. Curran Associates, Inc. http://papers.nips.cc/paper/6379-composing-graphical-models-with-neural-networks-for-structured-representations-and-fast-inference.pdf.

*Advances in Neural Information Processing Systems 30*, edited by I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, 6446–56. Curran Associates, Inc. http://papers.nips.cc/paper/7223-causal-effect-inference-with-deep-latent-variable-models.pdf.

*Advances In Neural Information Processing Systems*. http://arxiv.org/abs/1911.07420.

*Proceedings of the 27th ACM International Conference on Information and Knowledge Management*, 1679–82. CIKM ’18. New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3269206.3269267.

*Journal of Machine Learning Research*21 (188): 1–86. http://jmlr.org/papers/v21/19-1026.html.

*Advances in Neural Information Processing Systems*. Vol. 33. https://arxiv.org/abs/2002.03278.