Stop the war!Остановите войну!
for scientists:
Google
Google Scholar
Semantic Scholar
IA Scholar
CiteSeerX
ORCIDPrateek Jain 0002
Person information
- affiliation: Microsoft Research India
- affiliation (former): UT Austin, USA
- affiliation (former): IIT Kanpur, India
Other persons with the same name
- Prateek Jain — disambiguation page
- Prateek Jain 0001 — Nuance Research, Sunnyvale, CA, USA (and 2 more)
- Prateek Jain 0003 — Bell Labs, USA (and 1 more)
- Prateek Jain 0004 — Dhirubhai Ambani Institute of Information and Communication Technology
- Prateek Jain 0005 — University of California, Irvine, USA
- Prateek Jain 0006
![[0000-0002-8191-9785]](https://dblp.org/img/orcid-mark.12x12.png "0000-0002-8191-9785")
— Malaviya National Institute of Technology, Jaipur, India (and 1 more) - Prateek Jain 0007 — Jaypee Institute of Information Technology University, Noida, India
- Prateek Jain 0008 — Indian Institute of Technology Indore, Madhya Pradesh, India
- Prateek Jain 0009 — Worcester Polytechnic Institute, USA
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2022
[c104]Anish Acharya, Abolfazl Hashemi, Prateek Jain, Sujay Sanghavi, Inderjit S. Dhillon, Ufuk Topcu:
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent. AISTATS 2022: 11145-11168- [c103]Prateek Varshney, Abhradeep Thakurta, Prateek Jain:
(Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping. COLT 2022: 1126-1166 - [c102]Naman Agarwal, Syomantak Chaudhuri, Prateek Jain, Dheeraj Mysore Nagaraj, Praneeth Netrapalli:
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs. ICLR 2022 - [c101]S. Deepak Narayanan, Aditya Sinha, Prateek Jain, Purushottam Kar, Sundararajan Sellamanickam:
IGLU: Efficient GCN Training via Lazy Updates. ICLR 2022 - [i81]Kwangjun Ahn, Prateek Jain, Ziwei Ji, Satyen Kale, Praneeth Netrapalli, Gil I. Shamir:
Reproducibility in Optimization: Theoretical Framework and Limits. CoRR abs/2202.04598 (2022) - [i80]Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham M. Kakade, Prateek Jain, Ali Farhadi:
Matryoshka Representations for Adaptive Deployment. CoRR abs/2205.13147 (2022) - [i79]Xiyang Liu, Weihao Kong, Prateek Jain, Sewoong Oh:
DP-PCA: Statistically Optimal and Differentially Private PCA. CoRR abs/2205.13709 (2022) - [i78]Kushal Majmundar, Sachin Goyal, Praneeth Netrapalli, Prateek Jain:
MET: Masked Encoding for Tabular Data. CoRR abs/2206.08564 (2022) - [i77]Prateek Varshney, Abhradeep Thakurta, Prateek Jain:
(Nearly) Optimal Private Linear Regression via Adaptive Clipping. CoRR abs/2207.04686 (2022) - 2021
- [j12]Prateek Jain, Dheeraj M. Nagaraj, Praneeth Netrapalli:
Making the Last Iterate of SGD Information Theoretically Optimal. SIAM J. Optim. 31(2): 1108-1130 (2021) - [c100]Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang:
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. ICML 2021: 1877-1887 - [c99]Aadirupa Saha, Nagarajan Natarajan, Praneeth Netrapalli, Prateek Jain:
Optimal regret algorithm for Pseudo-1d Bandit Convex Optimization. ICML 2021: 9255-9264 - [c98]Harshay Shah, Prateek Jain, Praneeth Netrapalli:
Do Input Gradients Highlight Discriminative Features? NeurIPS 2021: 2046-2059 - [c97]Suhas S. Kowshik, Dheeraj Nagaraj, Prateek Jain, Praneeth Netrapalli:
Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems. NeurIPS 2021: 8518-8531 - [c96]Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh:
Statistically and Computationally Efficient Linear Meta-representation Learning. NeurIPS 2021: 18487-18500 - [c95]Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham M. Kakade, Ali Farhadi:
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes. NeurIPS 2021: 23900-23913 - [c94]Prateek Jain, John Rush, Adam D. Smith, Shuang Song, Abhradeep Guha Thakurta:
Differentially Private Model Personalization. NeurIPS 2021: 29723-29735 - [c93]Prateek Jain, Suhas S. Kowshik, Dheeraj Nagaraj, Praneeth Netrapalli:
Streaming Linear System Identification with Reverse Experience Replay. NeurIPS 2021: 30140-30152 - [i76]Aadirupa Saha, Nagarajan Natarajan, Praneeth Netrapalli, Prateek Jain:
Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization. CoRR abs/2102.07387 (2021) - [i75]Harshay Shah, Prateek Jain, Praneeth Netrapalli:
Do Input Gradients Highlight Discriminative Features? CoRR abs/2102.12781 (2021) - [i74]Prateek Jain, Suhas S. Kowshik, Dheeraj Nagaraj, Praneeth Netrapalli:
Streaming Linear System Identification with Reverse Experience Replay. CoRR abs/2103.05896 (2021) - [i73]Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh:
Sample Efficient Linear Meta-Learning by Alternating Minimization. CoRR abs/2105.08306 (2021) - [i72]Prateek Jain, Suhas S. Kowshik, Dheeraj Nagaraj, Praneeth Netrapalli:
Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems. CoRR abs/2105.11558 (2021) - [i71]Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham M. Kakade, Ali Farhadi:
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes. CoRR abs/2106.01487 (2021) - [i70]Anish Acharya, Abolfazl Hashemi, Prateek Jain, Sujay Sanghavi, Inderjit S. Dhillon, Ufuk Topcu:
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent. CoRR abs/2106.08882 (2021) - [i69]Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang:
Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. CoRR abs/2107.09802 (2021) - [i68]S. Deepak Narayanan, Aditya Sinha, Prateek Jain, Purushottam Kar, Sundararajan Sellamanickam:
IGLU: Efficient GCN Training via Lazy Updates. CoRR abs/2109.13995 (2021) - [i67]Naman Agarwal, Syomantak Chaudhuri, Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli:
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs. CoRR abs/2110.08440 (2021) - [i66]Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, Prateek Jain:
Node-Level Differentially Private Graph Neural Networks. CoRR abs/2111.15521 (2021) - 2020
- [c92]Sachin Goyal, Aditi Raghunathan, Moksh Jain, Harsha Vardhan Simhadri, Prateek Jain:
DROCC: Deep Robust One-Class Classification. ICML 2020: 3711-3721 - [c91]Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham M. Kakade, Ali Farhadi:
Soft Threshold Weight Reparameterization for Learnable Sparsity. ICML 2020: 5544-5555 - [c90]Dheeraj Nagaraj, Xian Wu, Guy Bresler, Prateek Jain, Praneeth Netrapalli:
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms. NeurIPS 2020 - [c89]Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain:
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference. NeurIPS 2020 - [c88]Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, Praneeth Netrapalli:
The Pitfalls of Simplicity Bias in Neural Networks. NeurIPS 2020 - [c87]Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh:
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method. NeurIPS 2020 - [i65]Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham M. Kakade, Ali Farhadi:
Soft Threshold Weight Reparameterization for Learnable Sparsity. CoRR abs/2002.03231 (2020) - [i64]Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain:
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference. CoRR abs/2002.11921 (2020) - [i63]Sachin Goyal, Aditi Raghunathan, Moksh Jain, Harsha Vardhan Simhadri, Prateek Jain:
DROCC: Deep Robust One-Class Classification. CoRR abs/2002.12718 (2020) - [i62]Harshay Shah, Kaustav Tamuly, Aditi Raghunathan, Prateek Jain, Praneeth Netrapalli:
The Pitfalls of Simplicity Bias in Neural Networks. CoRR abs/2006.07710 (2020) - [i61]Guy Bresler, Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli, Xian Wu:
Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms. CoRR abs/2006.08916 (2020) - [i60]Bhaskar Mukhoty, Govind Gopakumar, Prateek Jain, Purushottam Kar:
Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems. CoRR abs/2006.14211 (2020) - [i59]Nagarajan Natarajan, Ajaykrishna Karthikeyan, Prateek Jain, Ivan Radicek, Sriram K. Rajamani, Sumit Gulwani, Johannes Gehrke:
Programming by Rewards. CoRR abs/2007.06835 (2020) - [i58]Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh:
Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method. CoRR abs/2010.01848 (2020)
2010 – 2019
- 2019
- [c86]Vivek Gupta, Rahul Wadbude, Nagarajan Natarajan, Harish Karnick, Prateek Jain, Piyush Rai:
Distributional Semantics Meets Multi-Label Learning. AAAI 2019: 3747-3754 - [c85]Bhaskar Mukhoty, Govind Gopakumar, Prateek Jain, Purushottam Kar:
Globally-convergent Iteratively Reweighted Least Squares for Robust Regression Problems. AISTATS 2019: 313-322 - [c84]Nagarajan Natarajan, Danny Simmons, Naren Datha, Prateek Jain, Sumit Gulwani:
Learning Natural Programs from a Few Examples in Real-Time. AISTATS 2019: 1714-1722 - [c83]Pengkai Zhu, Durmus Alp Emre Acar, Nan Feng, Prateek Jain, Venkatesh Saligrama:
Cost aware Inference for IoT Devices. AISTATS 2019: 2770-2779 - [c82]Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli:
Making the Last Iterate of SGD Information Theoretically Optimal. COLT 2019: 1752-1755 - [c81]Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain:
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression. COLT 2019: 2892-2897 - [c80]Rong Ge, Prateek Jain, Sham M. Kakade, Rahul Kidambi, Dheeraj M. Nagaraj, Praneeth Netrapalli:
Open Problem: Do Good Algorithms Necessarily Query Bad Points? COLT 2019: 3190-3193 - [c79]Dheeraj Nagaraj, Prateek Jain, Praneeth Netrapalli:
SGD without Replacement: Sharper Rates for General Smooth Convex Functions. ICML 2019: 4703-4711 - [c78]Kai Zhong, Zhao Song, Prateek Jain, Inderjit S. Dhillon:
Provable Non-linear Inductive Matrix Completion. NeurIPS 2019: 11435-11445 - [c77]Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh:
Efficient Algorithms for Smooth Minimax Optimization. NeurIPS 2019: 12659-12670 - [c76]Don Kurian Dennis, Durmus Alp Emre Acar, Vikram Mandikal, Vinu Sankar Sadasivan, Venkatesh Saligrama, Harsha Vardhan Simhadri, Prateek Jain:
Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices. NeurIPS 2019: 12896-12906 - [c75]Shishir G. Patil, Don Kurian Dennis, Chirag Pabbaraju, Nadeem Shaheer, Harsha Vardhan Simhadri, Vivek Seshadri, Manik Varma, Prateek Jain:
GesturePod: Enabling On-device Gesture-based Interaction for White Cane Users. UIST 2019: 403-415 - [i57]Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma:
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network. CoRR abs/1901.02358 (2019) - [i56]Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli:
SGD without Replacement: Sharper Rates for General Smooth Convex Functions. CoRR abs/1903.01463 (2019) - [i55]Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, Prateek Jain:
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression. CoRR abs/1903.08192 (2019) - [i54]Prateek Jain, Dheeraj Nagaraj, Praneeth Netrapalli:
Making the Last Iterate of SGD Information Theoretically Optimal. CoRR abs/1904.12443 (2019) - [i53]Kiran Koshy Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh:
Efficient Algorithms for Smooth Minimax Optimization. CoRR abs/1907.01543 (2019) - [i52]Chirag Pabbaraju, Prateek Jain:
Learning Functions over Sets via Permutation Adversarial Networks. CoRR abs/1907.05638 (2019) - [i51]Sahil Bhatia, Saswat Padhi, Nagarajan Natarajan, Rahul Sharma, Prateek Jain:
OASIS: ILP-Guided Synthesis of Loop Invariants. CoRR abs/1911.11728 (2019) - 2018
- [j11]Saswat Padhi, Prateek Jain, Daniel Perelman, Oleksandr Polozov, Sumit Gulwani, Todd D. Millstein:
FlashProfile: a framework for synthesizing data profiles. Proc. ACM Program. Lang. 2(OOPSLA): 150:1-150:28 (2018) - [c74]Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford:
Accelerating Stochastic Gradient Descent for Least Squares Regression. COLT 2018: 545-604 - [c73]Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli:
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. COLT 2018: 3243-3270 - [c72]Ashwin Kalyan, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani:
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples. ICLR (Poster) 2018 - [c71]Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade:
On the insufficiency of existing momentum schemes for Stochastic Optimization. ICLR 2018 - [c70]Prateek Jain, Om Dipakbhai Thakkar, Abhradeep Thakurta:
Differentially Private Matrix Completion Revisited. ICML 2018: 2220-2229 - [c69]Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade:
On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization. ITA 2018: 1-9 - [c68]Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma:
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network. NeurIPS 2018: 9031-9042 - [c67]Raghav Somani, Chirag Gupta, Prateek Jain, Praneeth Netrapalli:
Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds. NeurIPS 2018: 10837-10847 - [c66]Don Kurian Dennis, Chirag Pabbaraju, Harsha Vardhan Simhadri, Prateek Jain:
Multiple Instance Learning for Efficient Sequential Data Classification on Resource-constrained Devices. NeurIPS 2018: 10976-10987 - [i50]Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli:
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form. CoRR abs/1803.00186 (2018) - [i49]Rahul Kidambi, Praneeth Netrapalli, Prateek Jain, Sham M. Kakade:
On the insufficiency of existing momentum schemes for Stochastic Optimization. CoRR abs/1803.05591 (2018) - [i48]Ashwin J. Vijayakumar, Abhishek Mohta, Oleksandr Polozov, Dhruv Batra, Prateek Jain, Sumit Gulwani:
Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples. CoRR abs/1804.01186 (2018) - [i47]Kai Zhong, Zhao Song, Prateek Jain, Inderjit S. Dhillon:
Nonlinear Inductive Matrix Completion based on One-layer Neural Networks. CoRR abs/1805.10477 (2018) - 2017
- [j10]Prateek Jain, Purushottam Kar:
Non-convex Optimization for Machine Learning. Found. Trends Mach. Learn. 10(3-4): 142-336 (2017) - [j9]Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford:
Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification. J. Mach. Learn. Res. 18: 223:1-223:42 (2017) - [j8]Prateek Jain, Ambuj Tewari, Inderjit S. Dhillon:
Partial Hard Thresholding. IEEE Trans. Inf. Theory 63(5): 3029-3038 (2017) - [c65]Apoorv Aggarwal, Sandip Ghoshal, Ankith M. S. Shetty, Suhit Sinha, Ganesh Ramakrishnan, Purushottam Kar, Prateek Jain:
Scalable Optimization of Multivariate Performance Measures in Multi-instance Multi-label Learning. AAAI 2017: 1698-1704 - [c64]Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli:
Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot. AISTATS 2017: 479-488 - [c63]Yeshwanth Cherapanamjeri, Prateek Jain, Praneeth Netrapalli:
Thresholding Based Outlier Robust PCA. COLT 2017: 593-628 - [c62]Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Venkata Krishna Pillutla, Aaron Sidford:
A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares). FSTTCS 2017: 2:1-2:10 - [c61]Kamalika Chaudhuri, Prateek Jain, Nagarajan Natarajan:
Active Heteroscedastic Regression. ICML 2017: 694-702 - [c60]Yeshwanth Cherapanamjeri, Kartik Gupta, Prateek Jain:
Nearly Optimal Robust Matrix Completion. ICML 2017: 797-805 - [c59]Chirag Gupta, Arun Sai Suggala, Ankit Goyal, Harsha Vardhan Simhadri, Bhargavi Paranjape, Ashish Kumar, Saurabh Goyal, Raghavendra Udupa, Manik Varma, Prateek Jain:
ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices. ICML 2017: 1331-1340 - [c58]Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon:
Recovery Guarantees for One-hidden-layer Neural Networks. ICML 2017: 4140-4149 - [c57]Kai Zhong, Prateek Jain, Ashish Kapoor:
Fast second-order cone programming for safe mission planning. ICRA 2017: 79-86 - [c56]Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar:
Consistent Robust Regression. NIPS 2017: 2110-2119 - [c55]Aditi Raghunathan, Prateek Jain, Ravishankar Krishnaswamy:
Learning Mixture of Gaussians with Streaming Data. NIPS 2017: 6605-6614 - [i46]Yeshwanth Cherapanamjeri, Prateek Jain, Praneeth Netrapalli:
Thresholding based Efficient Outlier Robust PCA. CoRR abs/1702.05571 (2017) - [i45]Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford:
Accelerating Stochastic Gradient Descent. CoRR abs/1704.08227 (2017) - [i44]Kai Zhong, Zhao Song, Prateek Jain, Peter L. Bartlett, Inderjit S. Dhillon:
Recovery Guarantees for One-hidden-layer Neural Networks. CoRR abs/1706.03175 (2017) - [i43]Aditi Raghunathan, Ravishankar Krishnaswamy, Prateek Jain:
Learning Mixture of Gaussians with Streaming Data. CoRR abs/1707.02391 (2017) - [i42]Saswat Padhi, Prateek Jain, Daniel Perelman, Oleksandr Polozov, Sumit Gulwani, Todd D. Millstein:
FlashProfile: Interactive Synthesis of Syntactic Profiles. CoRR abs/1709.05725 (2017) - [i41]Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Venkata Krishna Pillutla, Aaron Sidford:
A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares). CoRR abs/1710.09430 (2017) - [i40]Prateek Jain, Purushottam Kar:
Non-convex Optimization for Machine Learning. CoRR abs/1712.07897 (2017) - [i39]Prateek Jain, Om Thakkar, Abhradeep Thakurta:
Differentially Private Matrix Completion, Revisited. CoRR abs/1712.09765 (2017) - 2016
- [j7]Alekh Agarwal, Animashree Anandkumar, Prateek Jain, Praneeth Netrapalli:
Learning Sparsely Used Overcomplete Dictionaries via Alternating Minimization. SIAM J. Optim. 26(4): 2775-2799 (2016) - [c54]Anima Anandkumar, Prateek Jain, Yang Shi, U. N. Niranjan:
Tensor vs. Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations. AISTATS 2016: 268-276 - [c53]Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford:
Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm. COLT 2016: 1147-1164 - [c52]Vidyadhar Rao, Prateek Jain, C. V. Jawahar:
Diverse Yet Efficient Retrieval using Locality Sensitive Hashing. ICMR 2016: 189-196 - [c51]Prateek Jain, Nikhil Rao, Inderjit S. Dhillon:
Structured Sparse Regression via Greedy Hard Thresholding. NIPS 2016: 1516-1524 - [c50]Kai Zhong, Prateek Jain, Inderjit S. Dhillon:
Mixed Linear Regression with Multiple Components. NIPS 2016: 2190-2198 - [c49]Fan Yang, Rina Foygel Barber, Prateek Jain, John D. Lafferty:
Selective inference for group-sparse linear models. NIPS 2016: 2469-2477 - [c48]Nagarajan Natarajan, Prateek Jain:
Regret Bounds for Non-decomposable Metrics with Missing Labels. NIPS 2016: 2874-2882 - [e1]Madhav V. Marathe, Mukesh K. Mohania, Mausam, Prateek Jain:
Proceedings of the 3rd IKDD Conference on Data Science, CODS 2016, Pune, India, March 13-16, 2016. ACM 2016, ISBN 978-1-4503-4217-9 [contents] - [i38]Prateek Jain, Nikhil Rao, Inderjit S. Dhillon:
Structured Sparse Regression via Greedy Hard-Thresholding. CoRR abs/1602.06042 (2016) - [i37]Prateek Jain, Chi Jin, Sham M. Kakade, Praneeth Netrapalli, Aaron Sidford:
Matching Matrix Bernstein with Little Memory: Near-Optimal Finite Sample Guarantees for Oja's Algorithm. CoRR abs/1602.06929 (2016) - [i36]Prateek Jain, Nagarajan Natarajan:
Regret Bounds for Non-decomposable Metrics with Missing Labels. CoRR abs/1606.02077 (2016) - [i35]Yeshwanth Cherapanamjeri, Kartik Gupta, Prateek Jain:
Nearly-optimal Robust Matrix Completion. CoRR abs/1606.07315 (2016) - [i34]Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, Purushottam Kar:
Efficient and Consistent Robust Time Series Analysis. CoRR abs/1607.00146 (2016) - [i33]Kai Zhong, Prateek Jain, Ashish Kapoor:
Fast Second-order Cone Programming for Safe Mission Planning. CoRR abs/1609.05243 (2016) - [i32]Prateek Jain, Sham M. Kakade, Rahul Kidambi, Praneeth Netrapalli, Aaron Sidford:
Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging. CoRR abs/1610.03774 (2016) - 2015
- [j6]Praneeth Netrapalli, Prateek Jain, Sujay Sanghavi:
Phase Retrieval Using Alternating Minimization. IEEE Trans. Signal Process. 63(18): 4814-4826 (2015) - [c47]Kai Zhong, Prateek Jain, Inderjit S. Dhillon:
Efficient Matrix Sensing Using Rank-1 Gaussian Measurements. ALT 2015: 3-18 - [c46]Prateek Jain, Praneeth Netrapalli:
Fast Exact Matrix Completion with Finite Samples. COLT 2015: 1007-1034 - [c45]Purushottam Kar, Harikrishna Narasimhan, Prateek Jain:
Surrogate Functions for Maximizing Precision at the Top. ICML 2015: 189-198 - [c44]Harikrishna Narasimhan, Purushottam Kar, Prateek Jain:
Optimizing Non-decomposable Performance Measures: A Tale of Two Classes. ICML 2015: 199-208 - [c43]Kush Bhatia, Prateek Jain, Purushottam Kar:
Robust Regression via Hard Thresholding. NIPS 2015: 721-729 - [c42]Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, Prateek Jain:
Sparse Local Embeddings for Extreme Multi-label Classification. NIPS 2015: 730-738 - [c41]Prateek Jain, Nagarajan Natarajan, Ambuj Tewari:
Predtron: A Family of Online Algorithms for General Prediction Problems. NIPS 2015: 1009-1017 - [c40]Prateek Jain, Ambuj Tewari:
Alternating Minimization for Regression Problems with Vector-valued Outputs. NIPS 2015: 1126-1134 - [c39]Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi:
Tighter Low-rank Approximation via Sampling the Leveraged Element. SODA 2015: 902-920 - [i31]Prateek Jain, Vivek Kulkarni, Abhradeep Thakurta, Oliver Williams:
To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout. CoRR abs/1503.02031 (2015) - [i30]Harikrishna Narasimhan, Purushottam Kar, Prateek Jain:
Optimizing Non-decomposable Performance Measures: A Tale of Two Classes. CoRR abs/1505.06812 (2015) - [i29]Purushottam Kar, Harikrishna Narasimhan, Prateek Jain:
Surrogate Functions for Maximizing Precision at the Top. CoRR abs/1505.06813 (2015) - [i28]Kush Bhatia, Prateek Jain, Purushottam Kar:
Robust Regression via Hard Thresholding. CoRR abs/1506.02428 (2015) - [i27]Kush Bhatia, Himanshu Jain, Purushottam Kar, Prateek Jain, Manik Varma:
Locally Non-linear Embeddings for Extreme Multi-label Learning. CoRR abs/1507.02743 (2015) - [i26]