About
 

Kristjan Greenewald

Research Staff Member

CV Google Scholar Website LinkedIn

Who they work with

Categories

Bayesian Modeling Causal Inference Optimal Transport

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.

Top Work

Causal inference is expensive. Here’s an algorithm for fixing that.

Causal inference is expensive. Here’s an algorithm for fixing that.

Causal Inference

Publications with the MIT-IBM Watson AI Lab

k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension
k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension
NeurIPS
 
Entropic Causal Inference: Graph Identifiability
Entropic Causal Inference: Graph Identifiability
ICML
 
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets
ICML
 
Sliced Mutual Information: A Scalable Measure of Statistical Dependence
Sliced Mutual Information: A Scalable Measure of Statistical Dependence
NeurIPS
 
Measuring Generalization with Optimal Transport
Measuring Generalization with Optimal Transport
NeurIPS
 
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation
AISTATSMachine Learning
 
The Computational Limits of Deep Learning
The Computational Limits of Deep Learning
Efficient AIDeep Learning
 
Active Structure Learning of Causal DAGs via Directed Clique Trees
Active Structure Learning of Causal DAGs via Directed Clique Trees
Causal Inference
 
Entropic Causal Inference: Identifiability and Finite Sample Results
Entropic Causal Inference: Identifiability and Finite Sample Results
Causal Inference
 
Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance
Asymptotic Guarantees for Generative Modeling based on the Smooth Wasserstein Distance
Bayesian Modeling
 
Gaussian-Smoothed Optimal Transport: Metric Structure and Statistical Efficiency
Gaussian-Smoothed Optimal Transport: Metric Structure and Statistical Efficiency
AISTATSOptimal Transport
 
Statistical Model Aggregation via Parameter Matching
Statistical Model Aggregation via Parameter Matching
NeurIPS
 
Sample Efficient Active Learning of Causal Trees
Sample Efficient Active Learning of Causal Trees
NeurIPS
 
SPAHM: Parameter matching for model fusion
SPAHM: Parameter matching for model fusion
Bayesian Modeling
 
Causal inference is expensive. Here’s an algorithm for fixing that.
Causal inference is expensive. Here’s an algorithm for fixing that.
Causal Inference
 
Estimating Information Flow in Deep Neural Networks
Estimating Information Flow in Deep Neural Networks
ICML
 
Bayesian Nonparametric Federated Learning of Neural Networks
Bayesian Nonparametric Federated Learning of Neural Networks
Federated Learning
 
Action Centered Contextual Bandits
Action Centered Contextual Bandits
Deep Learning
 
Ensemble Estimation of Information Divergence
Ensemble Estimation of Information Divergence
Information Theory