Alexis Bellot (DeepMind): A Causal Approach to Transfer Learning in Machine Learning

Alexis Bellot is a research scientist at Google DeepMind in London, UK. In this talk, Alexis discusses the problem of transfer learning through the lens of partial transportability, that combines data from source domains and assumptions about the data generating mechanisms, encoded in causal diagrams, to provide a guarantee on out-of-distribution performance of classification models.