Sotabase

Career

· Postdoctoral Research Scientist, Columbia University2017–2018
· Associate Professor, Columbia University2015–
· Researcher, Microsoft Research2010–2014
· CTO and Co-founder, Pyte (acquired by Open Hands AI)

Publications (54)

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Neural Information Processing Systems · 2019
595
cited
Practical and Optimal LSH for Angular Distance
Neural Information Processing Systems · 2015
526
cited
Optimal Data-Dependent Hashing for Approximate Near Neighbors
Symposium on the Theory of Computing · 2015
309
cited
Adversarial examples from computational constraints
International Conference on Machine Learning · 2018
236
cited
Randomized Smoothing of All Shapes and Sizes
International Conference on Machine Learning · 2020
228
cited
Beyond Locality-Sensitive Hashing
ACM-SIAM Symposium on Discrete Algorithms · 2013
201
cited
Approximate Nearest Neighbor Search in High Dimensions
International Congress of Mathematicans · 2018
179
cited
Performance of Johnson-Lindenstrauss transform for k-means and k-medians clustering
Symposium on the Theory of Computing · 2018
145
cited
Graph Partitioning with Natural Cuts
IEEE International Parallel and Distributed Processing Symposium · 2011
143
cited
Optimal Hashing-based Time-Space Trade-offs for Approximate Near Neighbors
ACM-SIAM Symposium on Discrete Algorithms · 2016
135
cited
Weighted low rank approximations with provable guarantees
Symposium on the Theory of Computing · 2016
107
cited
Learning Space Partitions for Nearest Neighbor Search
IEEE Data Engineering Bulletin · 2019
103
cited
Maliciously Secure Matrix Multiplication with Applications to Private Deep Learning
IACR Cryptology ePrint Archive · 2020
82
cited
SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Search
IACR Cryptology ePrint Archive · 2019
66
cited
Scalable Nearest Neighbor Search for Optimal Transport
International Conference on Machine Learning · 2019
61
cited
Tight Lower Bounds for Data-Dependent Locality-Sensitive Hashing
International Symposium on Computational Geometry · 2015
52
cited
On the Complexity of Inner Product Similarity Join
ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems · 2015
49
cited
Sketching and Embedding are Equivalent for Norms
Symposium on the Theory of Computing · 2014
45
cited
LSH Forest: Practical Algorithms Made Theoretical
ACM-SIAM Symposium on Discrete Algorithms · 2017
44
cited
Approximate near neighbors for general symmetric norms
Symposium on the Theory of Computing · 2016
40
cited
Sotabase
Ilya Razenshteyn | Researcher Profile | Sotabase | Sotabase