Causal inference is expensive. Here’s an algorithm for fixing that.
Kristjan Greenewald
Research Staff Member

Who they work with
Categories
My interests lie broadly in applying information theory and statistics to both practical and theoretical machine learning problems. Areas of interest include learning theory, causal inference, online learning and decision making, and robust ML. I received my PhD from the University of Michigan in 2017 focusing on signal processing and machine learning, and was a postdoctoral research fellow at the Harvard University Statistics department (2017) before joining IBM Research in 2018.
Publications with the MIT-IBM Watson AI Lab
Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier
Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance
Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance
Gaussian-Smoothed Optimal Transport: Metric Structure and Statistical Efficiency
Gaussian-Smoothed Optimal Transport: Metric Structure and Statistical Efficiency