Sotabase

Career

· Chancellor's Professor, Massachusetts Institute of Technology2024–
· Norbert Wiener Professor of Mathematics, Massachusetts Institute of Technology2021–
· Associate Professor with Tenure, Massachusetts Institute of Technology2019–2021
· Assistant Professor, Massachusetts Institute of Technology2013–2017
· Senior Postdoc, Princeton University2012–2013
· NSF Computing and Innovation Fellow, Institute for Advanced Study2011–2013
· PhD in Computer Science, Massachusetts Institute of Technology2007–2011
· S.M. in Computer Science, Massachusetts Institute of Technology2007–2009
· B.S. in Electrical and Computer Engineering, Cornell University2003–2007

Publications (281)

Robust Estimators in High Dimensions without the Computational Intractability
IEEE Annual Symposium on Foundations of Computer Science · 2016
538
cited
A Practical Algorithm for Topic Modeling with Provable Guarantees
International Conference on Machine Learning · 2012
454
cited
Learning Topic Models -- Going beyond SVD
IEEE Annual Symposium on Foundations of Computer Science · 2012
452
cited
Computing a nonnegative matrix factorization -- provably
Symposium on the Theory of Computing · 2011
413
cited
Settling the Polynomial Learnability of Mixtures of Gaussians
IEEE Annual Symposium on Foundations of Computer Science · 2010
351
cited
A Nearly Tight Sum-of-Squares Lower Bound for the Planted Clique Problem
IEEE Annual Symposium on Foundations of Computer Science · 2016
266
cited
Being Robust (in High Dimensions) Can Be Practical
International Conference on Machine Learning · 2017
265
cited
Efficiently learning mixtures of two Gaussians
Symposium on the Theory of Computing · 2010
226
cited
New Algorithms for Learning Incoherent and Overcomplete Dictionaries
Annual Conference Computational Learning Theory · 2013
207
cited
Simple, Efficient, and Neural Algorithms for Sparse Coding
Annual Conference Computational Learning Theory · 2015
200
cited
Super-resolution, Extremal Functions and the Condition Number of Vandermonde Matrices
Symposium on the Theory of Computing · 2014
187
cited
Smoothed analysis of tensor decompositions
Symposium on the Theory of Computing · 2013
156
cited
Robustly Learning a Gaussian: Getting Optimal Error, Efficiently
ACM-SIAM Symposium on Discrete Algorithms · 2017
139
cited
Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models
Annals of Statistics · 2018
120
cited
Algorithms and Hardness for Robust Subspace Recovery
Annual Conference Computational Learning Theory · 2012
117
cited
Some Results on Greedy Embeddings in Metric Spaces
2008 49th Annual IEEE Symposium on Foundations of Computer Science · 2008
111
cited
Noisy tensor completion via the sum-of-squares hierarchy
Mathematical programming · 2015
110
cited
An information complexity approach to extended formulations
Symposium on the Theory of Computing · 2013
104
cited
Approximation Algorithms for Multicommodity-Type Problems with Guarantees Independent of the Graph Size
2009 50th Annual IEEE Symposium on Foundations of Computer Science · 2009
99
cited
Distilling Model Failures as Directions in Latent Space
International Conference on Learning Representations · 2022
98
cited
Sotabase
Ankur Moitra | Researcher Profile | Sotabase | Sotabase