Sotabase

Career

· Assistant Professor, New York University (NYU)2026–
· Faculty Member and Canada CIFAR AI Chair, Vector Institute2023–
· Faculty Affiliate, Vector Institute2020–2023
· Assistant Professor, University of Waterloo2019–
· PhD Student, Massachusetts Institute of Technology2018–
· Microsoft Research Fellow, Simons Institute for the Theory of Computing2018–2019
· S.M., Massachusetts Institute of Technology2014–
· S.M. in Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)2014–
· B.S. in Computer Science and Electrical and Computer Engineering, Cornell University2012–
· Ph.D. in Electrical Engineering and Computer Science, Massachusetts Institute of Technology (MIT)2012–2018

Publications (125)

Robust Estimators in High Dimensions without the Computational Intractability
IEEE Annual Symposium on Foundations of Computer Science · 2016
538
cited
Differentially Private Fine-tuning of Language Models
International Conference on Learning Representations · 2021
455
cited
Remember What You Want to Forget: Algorithms for Machine Unlearning
Neural Information Processing Systems · 2021
405
cited
The Discrete Gaussian for Differential Privacy
Neural Information Processing Systems · 2020
310
cited
Sever: A Robust Meta-Algorithm for Stochastic Optimization
International Conference on Machine Learning · 2018
309
cited
Being Robust (in High Dimensions) Can Be Practical
International Conference on Machine Learning · 2017
265
cited
Optimal Testing for Properties of Distributions
Neural Information Processing Systems · 2015
171
cited
Privately Learning High-Dimensional Distributions
Annual Conference Computational Learning Theory · 2018
163
cited
Robustly Learning a Gaussian: Getting Optimal Error, Efficiently
ACM-SIAM Symposium on Discrete Algorithms · 2017
139
cited
CoinPress: Practical Private Mean and Covariance Estimation
Neural Information Processing Systems · 2020
126
cited
Private Mean Estimation of Heavy-Tailed Distributions
Annual Conference Computational Learning Theory · 2020
108
cited
Testing Ising Models
IEEE Transactions on Information Theory · 2016
106
cited
Private Hypothesis Selection
IEEE Transactions on Information Theory · 2019
98
cited
Considerations for Differentially Private Learning with Large-Scale Public Pretraining
International Conference on Machine Learning · 2022
97
cited
Faster and Sample Near-Optimal Algorithms for Proper Learning Mixtures of Gaussians
Annual Conference Computational Learning Theory · 2013
92
cited
Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
Neural Information Processing Systems · 2020
88
cited
The structure of optimal private tests for simple hypotheses
Symposium on the Theory of Computing · 2018
84
cited
Efficient mean estimation with pure differential privacy via a sum-of-squares exponential mechanism
Symposium on the Theory of Computing · 2021
67
cited
An analysis of one-dimensional schelling segregation
Symposium on the Theory of Computing · 2012
65
cited
Robustness Implies Privacy in Statistical Estimation
Symposium on the Theory of Computing · 2022
62
cited
Sotabase