Sotabase

Career

· Associate Professor, Stanford University2013–
· Postdoctoral Researcher, Microsoft Research, New England2012–2013
· PhD in Computer Science, UC Berkeley2012–
· Intern, IBM Research, Almaden2010–
· Intern, Microsoft Research, New England2009–
· Graduate Student Researcher and Teaching Assistant, University of California, Berkeley2007–2012
· Bachelor of Arts, Mathematics, Harvard University2006–
· Master of Science, Computer Science, Harvard University2006–

Publications (288)

What Can Transformers Learn In-Context? A Case Study of Simple Function Classes
Neural Information Processing Systems · 2022
683
cited
Making AI Forget You: Data Deletion in Machine Learning
Neural Information Processing Systems · 2019
616
cited
Settling the Polynomial Learnability of Mixtures of Gaussians
IEEE Annual Symposium on Foundations of Computer Science · 2010
351
cited
Estimating the unseen: an n/log(n)-sample estimator for entropy and support size, shown optimal via new CLTs
Symposium on the Theory of Computing · 2011
312
cited
Learning from untrusted data
Symposium on the Theory of Computing · 2016
310
cited
Optimal Algorithms for Testing Closeness of Discrete Distributions
ACM-SIAM Symposium on Discrete Algorithms · 2013
240
cited
An Automatic Inequality Prover and Instance Optimal Identity Testing
IEEE Annual Symposium on Foundations of Computer Science · 2014
236
cited
Efficiently learning mixtures of two Gaussians
Symposium on the Theory of Computing · 2010
226
cited
Learning Polynomials with Neural Networks
International Conference on Machine Learning · 2014
163
cited
Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process
Annual Conference Computational Learning Theory · 2019
161
cited
The Power of Linear Estimators
IEEE Annual Symposium on Foundations of Computer Science · 2011
153
cited
Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers
Information Technology Convergence and Services · 2017
143
cited
Estimating the Unseen
Neural Information Processing Systems · 2013
115
cited
A CLT and tight lower bounds for estimating entropy
Electron. Colloquium Comput. Complex. · 2010
99
cited
Finding Correlations in Subquadratic Time, with Applications to Learning Parities and Juntas
IEEE Annual Symposium on Foundations of Computer Science · 2012
95
cited
Designing Network Protocols for Good Equilibria
SIAM journal on computing (Print) · 2010
92
cited
On the Generalization Effects of Linear Transformations in Data Augmentation
International Conference on Machine Learning · 2020
88
cited
Memory, Communication, and Statistical Queries
Annual Conference Computational Learning Theory · 2016
87
cited
Finding Correlations in Subquadratic Time, with Applications to Learning Parities and the Closest Pair Problem
Journal of the ACM · 2015
83
cited
Martian subsurface properties and crater formation processes inferred from fresh impact crater geometries
2006
83
cited
Sotabase