Tag: machine-learning
All the articles with the tag "machine-learning".
-
Double Machine Learning: Residualize Twice, Then Regress
Plugging a flexible ML fit into a causal regression biases the estimate through regularization and overfitting. Residualizing both outcome and treatment, out of fold, repairs the estimation. It does nothing for confounders you never measured.
-
You Are Your Relationships: The Yoneda Lemma
Category theory's most famous lemma says something almost philosophical: an object is completely determined by its relationships to everything else. The same idea quietly powers embeddings, interfaces, and most good abstraction.