About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Bernhard Schölkopf
- sl:arxiv_num : 2102.11107
- sl:arxiv_published : 2021-02-22T15:26:57Z
- sl:arxiv_summary : The two fields of machine learning and graphical causality arose and
developed separately. However, there is now cross-pollination and increasing
interest in both fields to benefit from the advances of the other. In the
present paper, we review fundamental concepts of causal inference and relate
them to crucial open problems of machine learning, including transfer and
generalization, thereby assaying how causality can contribute to modern machine
learning research. This also applies in the opposite direction: we note that
most work in causality starts from the premise that the causal variables are
given. A central problem for AI and causality is, thus, causal representation
learning, the discovery of high-level causal variables from low-level
observations. Finally, we delineate some implications of causality for machine
learning and propose key research areas at the intersection of both
communities.@en
- sl:arxiv_title : Towards Causal Representation Learning@en
- sl:arxiv_updated : 2021-02-22T15:26:57Z
- sl:bookmarkOf :
- sl:creationDate : 2021-07-15
- sl:creationTime : 2021-07-15T00:29:21Z
- sl:relatedDoc : http://www.semanlink.net/doc/2021/05/making_sense_of_raw_input
Documents with similar tags (experimental)