引用次数
引用: 6,854
H-指数: 25
I10-指数 : 35
出版物: 53
Universal Matrix Completion
Srinadh Bhojanapalli , Prateek Jain
arXiv: Machine Learning
25
2014
Global Optimality of Local Search for Low Rank Matrix Recovery
Behnam Neyshabur , Srinadh Bhojanapalli , Nathan Srebro
arXiv: Machine Learning
376
2016
Single Pass PCA of Matrix Products
Shanshan Wu , Srinadh Bhojanapalli , Sujay Sanghavi , Alexandros G Dimakis
neural information processing systems 29 2577 -2585
8
2016
Implicit Regularization in Matrix Factorization
Behnam Neyshabur , Srinadh Bhojanapalli , Nathan Srebro , Suriya Gunasekar
arXiv: Machine Learning
347
2017
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Srinadh Bhojanapalli , James Demmel , Kurt Keutzer , Xiaodan Song
arXiv: Learning
567
2019
Tighter Low-rank Approximation via Sampling the Leveraged Element
Srinadh Bhojanapalli , Sujay Sanghavi , Prateek Jain
arXiv: Data Structures and Algorithms
41
2014
Dropping Convexity for Faster Semi-definite Optimization
Srinadh Bhojanapalli , Sujay Sanghavi , Anastasios Kyrillidis
conference on learning theory 530 -582
56
2016
Completing any low-rank matrix, provably
Srinadh Bhojanapalli , Sujay Sanghavi , Rachel Ward , Yudong Chen
Journal of Machine Learning Research 16 ( 1) 2999 -3034
80
2015
Exploring Generalization in Deep Learning
Behnam Neyshabur , Srinadh Bhojanapalli , Nathan Srebro , David McAllester
neural information processing systems 30 5947 -5956
987
2017
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form
Srinadh Bhojanapalli , Nicolas Boumal , Praneeth Netrapalli , Prateek Jain
conference on learning theory 3243 -3270
5
2018
Are Transformers universal approximators of sequence-to-sequence functions?
Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar
arXiv: Learning
120
2019
Concise Multi-head Attention Models
Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank Reddi , Sanjiv Kumar
2019
Low-Rank Bottleneck in Multi-head Attention Models
Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar
arXiv: Learning
37
2020
Does label smoothing mitigate label noise
Srinadh Bhojanapalli , Sanjiv Kumar , Michal Lukasik , Aditya Krishna Menon
arXiv: Learning
179
2020
Semantic Label Smoothing for Sequence to Sequence Problems.
Srinadh Bhojanapalli , Seungyeon Kim , Felix Yu , Sanjiv Kumar
arXiv: Computation and Language
12
2020
An efficient nonconvex reformulation of stagewise convex optimization problems
Krishnamurthy Dvijotham , Srinadh Bhojanapalli , Rudy R. Bunel , Oliver Hinder
neural information processing systems 33 8247 -8258
8
2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers.
Srinadh Bhojanapalli , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar
neural information processing systems 33 13783 -13794
31
2020
Modifying Memories in Transformer Models
Srinadh Bhojanapalli , Ankit Singh Rawat , Felix Yu , Sanjiv Kumar
arXiv: Computation and Language
26
2021
On the Reproducibility of Neural Network Predictions
Srinadh Bhojanapalli , Andreas Veit , Aditya Krishna Menon , Ankit Singh Rawat
arXiv: Learning
19
2021
Understanding Robustness of Transformers for Image Classification.
Thomas Unterthiner , Srinadh Bhojanapalli , Andreas Veit , Ayan Chakrabarti
arXiv: Computer Vision and Pattern Recognition
160
2021