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
Journal ArticleDOI
Private and Efficient Meta-Learning with Low Rank and Sparse Decomposition
Soumyabrata Pal,Prateek Varshney,Prateek Jain,Abhradeep Guha Thakurta,Gagan Madan,Gaurav Aggarwal,Pradeep Shenoy,Gaurav Srivastava +7 more
TL;DR: A novel meta-learning framework that combines both the techniques to enable handling of a large number of data-starved tasks and extends AMHT-LRS to ensure that it preserves privacy of each individual user in the dataset, while still ensuring strong generalization with nearly optimal number of samples.
Posted Content
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
Aditya Kusupati,Matthew Wallingford,Vivek Ramanujan,Raghav Somani,Jae Sung Park,Krishna Pillutla,Prateek Jain,Sham M. Kakade,Ali Farhadi +8 more
TL;DR: In this paper, the authors propose a method for learning low-dimensional binary codes (LLC) for instances as well as classes, which does not require any side-information, like annotated attributes or label meta-data.
Large-scale Model Personalization via Low Rank and Sparse decomposition
Soumyabrata Pal,Prateeksha Varshney,Prateek Jain,Abhradeep Guha Thakurta,Gagan Madan,Gaurav Aggarwal,Pradeep Shenoy,Gaurav Srivastava +7 more
TL;DR: In this paper , the authors propose a meta-learning style approach that models network weights as a sum of low-rank and sparse matrices, which is up to two orders of magnitude more scalable than user-specific finetuning of model.
Proceedings ArticleDOI
Optimal Algorithms for Latent Bandits with Cluster Structure
TL;DR: In this article , the authors consider the problem of latent bandits with cluster structure where there are multiple users, each with an associated multi-armed bandit problem, and propose LATTICE (Latent bAndiTs via maTrIx ComplEtion) which allows exploitation of the latent cluster structure to provide the minimax optimal regret of