P
Prateek Jain
Researcher at Google
Publications - 200
Citations - 12983
Prateek Jain is an academic researcher from Google. The author has contributed to research in topics: Matrix (mathematics) & Computer science. The author has an hindex of 51, co-authored 173 publications receiving 11698 citations. Previous affiliations of Prateek Jain include Microsoft & University of California, Berkeley.
Papers
More filters
Proceedings Article
Differentially Private Learning with Kernels
Prateek Jain,Abhradeep Thakurta +1 more
TL;DR: This paper derives differentially private learning algorithms with provable "utility" or error bounds from the standard learning model of releasing different private predictor using three simple but practical models.
Proceedings Article
Robust Regression via hard thresholding
TL;DR: A simple hard-thresholding algorithm called TORRENT is studied which, under mild conditions on X, can recover w* exactly even if b corrupts the response variables in an adversarial manner, i.e. both the support and entries of b are selected adversarially after observing X and w*.
Proceedings Article
One-Bit Compressed Sensing: Provable Support and Vector Recovery
TL;DR: This paper proposes two novel and efficient solutions based on two combinatorial structures: union free families of sets and expanders for support recovery and the first method to recover a sparse vector using a near optimal number of measurements.
Proceedings Article
On Iterative Hard Thresholding Methods for High-dimensional M-Estimation
TL;DR: In this paper, the authors provide the first analysis for iterative hard thresholding (IHT) methods in the high dimensional statistical setting, and their bounds are tight and match known minimax lower bounds.
Journal IssueDOI
Simultaneous Unsupervised Learning of Disparate Clusterings
TL;DR: This paper proposes a new regularized factorial-learning framework that is more suitable for capturing the notion of disparate clusterings in modern, high-dimensional datasets and provides kernelized version of both of the algorithms.