activity
20162022
most citedBayesian Nonparametric Federated Learning of Neural Networks

147 citations · 182 across the 12 of their papers we have counts for

collaborators

18 papers

cs.LG2022

Outlier-Robust Group Inference via Gradient Space Clustering

Yuchen Zeng, Kristjan Greenewald, Kangwook Lee +2

Traditional machine learning models focus on achieving good performance on the overall training distribution, but they often underperform on minority groups. Existing methods can i…

cs.LG20215 cited

Measuring Generalization with Optimal Transport

Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald +2

Understanding the generalization of deep neural networks is one of the most important tasks in deep learning. Although much progress has been made, theoretical error bounds still o…

stat.ML2021

Entropic Causal Inference: Identifiability and Finite Sample Results

Spencer Compton, Murat Kocaoglu, Kristjan Greenewald +1

Entropic causal inference is a framework for inferring the causal direction between two categorical variables from observational data. The central assumption is that the amount of…

math.ST2020

-Variance: A Clustered Notion of Variance

Justin Solomon, Kristjan Greenewald, Haikady N. Nagaraja

We introduce -variance, a generalization of variance built on the machinery of random bipartite matchings. -variance measures the expected cost of matching two sets of sa…

stat.ML20201 cited

High-Dimensional Feature Selection for Sample Efficient Treatment Effect Estimation

Kristjan Greenewald, Dmitriy Katz-Rogozhnikov, Karthik Shanmugam

The estimation of causal treatment effects from observational data is a fundamental problem in causal inference. To avoid bias, the effect estimator must control for all confounder…

stat.ME20203 cited

Active Structure Learning of Causal DAGs via Directed Clique Tree

Chandler Squires, Sara Magliacane, Kristjan Greenewald +3

A growing body of work has begun to study intervention design for efficient structure learning of causal directed acyclic graphs (DAGs). A typical setting is a causally sufficient…