Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
An efficient nonconvex reformulation of stagewise convex optimization problems

Oct 27, 2020
Rudy Bunel, Oliver Hinder, Srinadh Bhojanapalli, Krishnamurthy, Dvijotham

* First and second authors made equal contribution. To appear in Neurips 2020 

  Access Paper or Ask Questions

Coping with Label Shift via Distributionally Robust Optimisation

Oct 23, 2020
Jingzhao Zhang, Aditya Menon, Andreas Veit, Srinadh Bhojanapalli, Sanjiv Kumar, Suvrit Sra


  Access Paper or Ask Questions

Semantic Label Smoothing for Sequence to Sequence Problems

Oct 15, 2020
Michal Lukasik, Himanshu Jain, Aditya Krishna Menon, Seungyeon Kim, Srinadh Bhojanapalli, Felix Yu, Sanjiv Kumar


  Access Paper or Ask Questions

$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers

Jun 08, 2020
Chulhee Yun, Yin-Wen Chang, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

* 32 pages 

  Access Paper or Ask Questions

Does label smoothing mitigate label noise?

Mar 05, 2020
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar


  Access Paper or Ask Questions

Low-Rank Bottleneck in Multi-head Attention Models

Feb 17, 2020
Srinadh Bhojanapalli, Chulhee Yun, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

* 17 pages, 4 figures 

  Access Paper or Ask Questions

Are Transformers universal approximators of sequence-to-sequence functions?

Dec 20, 2019
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank J. Reddi, Sanjiv Kumar

* Accepted to ICLR 2020 

  Access Paper or Ask Questions

Stabilizing GAN Training with Multiple Random Projections

Jun 23, 2018
Behnam Neyshabur, Srinadh Bhojanapalli, Ayan Chakrabarti


  Access Paper or Ask Questions

Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks

May 30, 2018
Behnam Neyshabur, Zhiyuan Li, Srinadh Bhojanapalli, Yann LeCun, Nathan Srebro

* 19 pages, 8 figures 

  Access Paper or Ask Questions

Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form

Mar 01, 2018
Srinadh Bhojanapalli, Nicolas Boumal, Prateek Jain, Praneeth Netrapalli

* 24 pages 

  Access Paper or Ask Questions

A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks

Feb 23, 2018
Behnam Neyshabur, Srinadh Bhojanapalli, Nathan Srebro

* Accepted to ICLR 2018 

  Access Paper or Ask Questions

Exploring Generalization in Deep Learning

Jul 06, 2017
Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, Nathan Srebro

* 19 pages, 8 figures 

  Access Paper or Ask Questions

Implicit Regularization in Matrix Factorization

May 25, 2017
Suriya Gunasekar, Blake Woodworth, Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro


  Access Paper or Ask Questions

Single Pass PCA of Matrix Products

Oct 26, 2016
Shanshan Wu, Srinadh Bhojanapalli, Sujay Sanghavi, Alexandros G. Dimakis

* 24 pages, 4 figures, NIPS 2016 

  Access Paper or Ask Questions

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems

Oct 01, 2016
Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis, Sujay Sanghavi

* 28 pages 

  Access Paper or Ask Questions

Global Optimality of Local Search for Low Rank Matrix Recovery

May 27, 2016
Srinadh Bhojanapalli, Behnam Neyshabur, Nathan Srebro

* 21 pages, 3 figures 

  Access Paper or Ask Questions

Dropping Convexity for Faster Semi-definite Optimization

Apr 16, 2016
Srinadh Bhojanapalli, Anastasios Kyrillidis, Sujay Sanghavi

* 40 pages 

  Access Paper or Ask Questions

A New Sampling Technique for Tensors

Feb 19, 2015
Srinadh Bhojanapalli, Sujay Sanghavi

* 29 pages,3 figures 

  Access Paper or Ask Questions

Tighter Low-rank Approximation via Sampling the Leveraged Element

Oct 14, 2014
Srinadh Bhojanapalli, Prateek Jain, Sujay Sanghavi

* 36 pages, 3 figures, Extended abstract to appear in the proceedings of ACM-SIAM Symposium on Discrete Algorithms (SODA15) 

  Access Paper or Ask Questions

Completing Any Low-rank Matrix, Provably

Jul 21, 2014
Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, Rachel Ward

* Added a new necessary condition(Theorem 6) and a result on completion of row coherent matrices(Corollary 4). Partial results appeared in the International Conference on Machine Learning 2014, under the title 'Coherent Matrix Completion'. (34 pages, 4 figures) 

  Access Paper or Ask Questions

Universal Matrix Completion

Jul 11, 2014
Srinadh Bhojanapalli, Prateek Jain

* 22 pages, 2 figures 

  Access Paper or Ask Questions