Causality for Machine Learning
It addresses foundational issues in machine learning and AI by linking them to causality, which could impact the entire field, though it is more conceptual and incremental in establishing these connections.
The paper argues that the hard open problems in machine learning and AI are intrinsically related to causality, discussing how graphical causal inference, which originated from AI research, has and should establish connections with machine learning.
Graphical causal inference as pioneered by Judea Pearl arose from research on artificial intelligence (AI), and for a long time had little connection to the field of machine learning. This article discusses where links have been and should be established, introducing key concepts along the way. It argues that the hard open problems of machine learning and AI are intrinsically related to causality, and explains how the field is beginning to understand them.