Learning representations for counterfactual inference
Paper in proceeding, 2016

Observational studies are rising in importance due to the widespread accumulation of data in fields such as healthcare, education, employment and ecology. We consider the task of answering counterfactual questions such as, "Would this patient have lower blood sugar had she received a different medication?". We propose a new algorithmic framework for counterfactual inference which brings together ideas from domain adaptation and representation learning. In addition to a theoretical justification, we perform an empirical comparison with previous approaches to causal inference from observational data. Our deep learning algorithm significantly outperforms the previous state-of-the-art. © 2016 by the author(s).

Observational data

Observational study

Learning algorithms

Learning systems

Empirical - comparisons

Artificial intelligence

State of the art

Algorithmic framework

Causal inferences

Blood sugars

Domain adaptation


Fredrik Johansson

Chalmers, Computer Science and Engineering (Chalmers), Computing Science (Chalmers)

U. Shalit

New York University

D. Sontag

New York University

33rd International Conference on Machine Learning, ICML 2016, New York City, United States; 19 June 2016 through 24 June 2016

9781510829008 (ISBN)

Subject Categories

Computer and Information Science



More information