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
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy

Jul 13, 2020
Edward Moroshko, Suriya Gunasekar, Blake Woodworth, Jason D. Lee, Nathan Srebro, Daniel Soudry


  Access Paper or Ask Questions

Mirrorless Mirror Descent: A More Natural Discretization of Riemannian Gradient Flow

Apr 24, 2020
Suriya Gunasekar, Blake Woodworth, Nathan Srebro

* 10 pages 

  Access Paper or Ask Questions

Kernel and Rich Regimes in Overparametrized Models

Feb 24, 2020
Blake Woodworth, Suriya Gunasekar, Jason D. Lee, Edward Moroshko, Pedro Savarese, Itay Golan, Daniel Soudry, Nathan Srebro

* This updates and significantly extends a previous article (arXiv:1906.05827), Sections 6 and 7.1 are the most major additions. 30 pages. arXiv admin note: text overlap with arXiv:1906.05827 

  Access Paper or Ask Questions

Implicit Regularization of Normalization Methods

Nov 23, 2019
Xiaoxia Wu, Edgar Dobriban, Tongzheng Ren, Shanshan Wu, Zhiyuan Li, Suriya Gunasekar, Rachel Ward, Qiang Liu


  Access Paper or Ask Questions

Kernel and Deep Regimes in Overparametrized Models

Jun 13, 2019
Blake Woodworth, Suriya Gunasekar, Jason Lee, Daniel Soudry, Nathan Srebro

* 16 pages 

  Access Paper or Ask Questions

Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models

May 17, 2019
Mor Shpigel Nacson, Suriya Gunasekar, Jason D. Lee, Nathan Srebro, Daniel Soudry

* ICML Camera ready version 

  Access Paper or Ask Questions

On preserving non-discrimination when combining expert advice

Oct 28, 2018
Avrim Blum, Suriya Gunasekar, Thodoris Lykouris, Nathan Srebro

* To appear in NIPS 2018 

  Access Paper or Ask Questions

Characterizing Implicit Bias in Terms of Optimization Geometry

Oct 22, 2018
Suriya Gunasekar, Jason Lee, Daniel Soudry, Nathan Srebro

* (1) A bug in the proof of implicit bias for matrix factorization was fixed. v2 gives a characterization of the asymptotic bias of the factor matrices, while v1 made a stronger claim on the limit direction of the unfactored matrix. (2) v2 also includes new results on implicit bias of mirror descent with realizable affine constraints 

  Access Paper or Ask Questions

Convergence of Gradient Descent on Separable Data

Jun 12, 2018
Mor Shpigel Nacson, Jason Lee, Suriya Gunasekar, Pedro H. P. Savarese, Nathan Srebro, Daniel Soudry

* Added empirical results of experiments on deep networks (Appendix E). In addition, minor typos and phrasing mistakes were fixed 

  Access Paper or Ask Questions

Implicit Bias of Gradient Descent on Linear Convolutional Networks

Jun 01, 2018
Suriya Gunasekar, Jason Lee, Daniel Soudry, Nathan Srebro


  Access Paper or Ask Questions

The Implicit Bias of Gradient Descent on Separable Data

Mar 21, 2018
Daniel Soudry, Elad Hoffer, Mor Shpigel Nacson, Suriya Gunasekar, Nathan Srebro

* Journal version (previous version appeared as conference paper in ICLR ). Main improvements: We proved measure zero case for main theorem (with implication for the rates), and the multi-class case. Both were not covered in previous version 

  Access Paper or Ask Questions

Learning Non-Discriminatory Predictors

Nov 01, 2017
Blake Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, Nathan Srebro

* 28 pages 

  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

Preference Completion from Partial Rankings

Nov 14, 2016
Suriya Gunasekar, Oluwasanmi Koyejo, Joydeep Ghosh

* NIPS 2016 

  Access Paper or Ask Questions

Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization

Sep 20, 2016
Shalmali Joshi, Suriya Gunasekar, David Sontag, Joydeep Ghosh

* Presented at 2016 Machine Learning and Healthcare Conference (MLHC 2016), Los Angeles, CA 

  Access Paper or Ask Questions

Unified View of Matrix Completion under General Structural Constraints

Mar 29, 2016
Suriya Gunasekar, Arindam Banerjee, Joydeep Ghosh

* published in NIPS 2015. Advances in Neural Information Processing Systems 28, 2015 

  Access Paper or Ask Questions

Exponential Family Matrix Completion under Structural Constraints

Sep 15, 2015
Suriya Gunasekar, Pradeep Ravikumar, Joydeep Ghosh

* Gunasekar, Suriya, Pradeep Ravikumar, and Joydeep Ghosh. "Exponential family matrix completion under structural constraints". Proceedings of The 31st International Conference on Machine Learning, pp. 1917-1925, 2014 
* 20 pages, 9 figures 

  Access Paper or Ask Questions

Consistent Collective Matrix Completion under Joint Low Rank Structure

Apr 07, 2015
Suriya Gunasekar, Makoto Yamada, Dawei Yin, Yi Chang

* 19 pages, 3 figures 

  Access Paper or Ask Questions