Kristjan Greenewald

Title

Research Staff Member

Bio

Kristjan Greenewald is a Research Staff Member at the MIT-IBM Watson AI Lab, Cambridge MA. His interests include optimal transport, causal inference, robustness, and statistical learning theory. He serves as Principal Investigator on multiple funded MIT-IBM research projects, and in 2022 received an IBM Outstanding Innovation Award for contributions to the MIT-IBM Watson AI Lab Membership Program.

Dr. Greenewald received his 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 (2017-2018) before joining IBM Research in 2018.

Publications

Active Structure Learning of Causal DAGs via Directed Clique Trees
- - Chandler Squires
  - Sara Magliacane
  - et al.
- 2020
- NeurIPS 2020
Entropic Causal Inference: Identifiability and Finite Sample Results Spencer Compton
- - Spencer Compton
  - Murat Kocaoglu
  - et al.
- 2020
- NeurIPS 2020
Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance
- - Ziv Goldfeld
  - Kristjan Greenewald
  - et al.
- 2020
- NeurIPS 2020
Convergence of Smoothed Empirical Measures with Applications to Entropy Estimation
- - Ziv Goldfeld
  - Kristjan Greenewald
  - et al.
- 2020
- IEEE Trans. Inf. Theory
Personalized heartsteps: A reinforcement learning algorithm for optimizing physical activity
- - Peng Liao
  - Kristjan Greenewald
  - et al.
- 2020
- ACM IMWUT
Statistical model aggregation via parameter matching
- - Mikhail Yurochkin
  - Mayank Agarwal
  - et al.
- 2019
- NeurIPS 2019
Sample efficient active learning of causal trees
- - Kristjan Greenewald
  - Dmitriy Katz-Rogozhnikov
  - et al.
- 2019
- NeurIPS 2019
Tensor graphical lasso (TeraLasso)
- - Kristjan Greenewald
  - Shuheng Zhou
  - et al.
- 2019
- JRSSB: Statistical Methodology
Optimality of the Plug-in Estimator for Differential Entropy Estimation under Gaussian Convolutions
- - Ziv Goldfeld
  - Kristjan Greenewald
  - et al.
- 2019
- ISIT 2019
Estimating information flow in deep neural networks
- - Ziv Goldfeld
  - Ewout van den Berg
  - et al.
- 2019
- ICML 2019

Visit Google Scholar

Patents

- 04 Dec 2023
- US
- 11836615
Bayesian Nonparametric Learning Of Neural Networks

Top collaborators

Kristjan Greenewald

Title

Bio

Publications

Active Structure Learning of Causal DAGs via Directed Clique Trees

Entropic Causal Inference: Identifiability and Finite Sample Results Spencer Compton

Asymptotic Guarantees for Generative Modeling Based on the Smooth Wasserstein Distance

Convergence of Smoothed Empirical Measures with Applications to Entropy Estimation

Personalized heartsteps: A reinforcement learning algorithm for optimizing physical activity

Statistical model aggregation via parameter matching

Sample efficient active learning of causal trees

Tensor graphical lasso (TeraLasso)

Optimality of the Plug-in Estimator for Differential Entropy Estimation under Gaussian Convolutions

Estimating information flow in deep neural networks

Patents

Bayesian Nonparametric Learning Of Neural Networks

Top collaborators

Mikhail Yurochkin

Youssef Mroueh

Mattia Rigotti

Subhro Das