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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Nathan Srebro

Eluder Dimension and Generalized Rank


Apr 14, 2021
Gene Li, Pritish Kamath, Dylan J. Foster, Nathan Srebro

* Technical Note 

  Access Paper or Ask Questions

Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels


Mar 01, 2021
Eran Malach, Pritish Kamath, Emmanuel Abbe, Nathan Srebro


  Access Paper or Ask Questions

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent


Feb 19, 2021
Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry

* 33 pages, 2 figures 

  Access Paper or Ask Questions

Adversarially Robust Learning with Unknown Perturbation Sets


Feb 03, 2021
Omar Montasser, Steve Hanneke, Nathan Srebro


  Access Paper or Ask Questions

The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication


Feb 02, 2021
Blake Woodworth, Brian Bullins, Ohad Shamir, Nathan Srebro

* 27 pages 

  Access Paper or Ask Questions

Does Invariant Risk Minimization Capture Invariance?


Jan 04, 2021
Pritish Kamath, Akilesh Tangella, Danica J. Sutherland, Nathan Srebro

* Code is available in the arXiv ancillary files, linked from this page 

  Access Paper or Ask Questions

Reducing Adversarially Robust Learning to Non-Robust PAC Learning


Oct 22, 2020
Omar Montasser, Steve Hanneke, Nathan Srebro

* To appear in NeurIPS 2020 

  Access Paper or Ask Questions

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

Predictive Value Generalization Bounds


Jul 09, 2020
Keshav Vemuri, Nathan Srebro

* 20 pages, 3 figures 

  Access Paper or Ask Questions

Minibatch vs Local SGD for Heterogeneous Distributed Learning


Jun 18, 2020
Blake Woodworth, Kumar Kshitij Patel, Nathan Srebro

* 34 pages 

  Access Paper or Ask Questions

On Uniform Convergence and Low-Norm Interpolation Learning


Jun 10, 2020
Lijia Zhou, D. J. Sutherland, Nathan Srebro

* 27 pages 

  Access Paper or Ask Questions

Efficiently Learning Adversarially Robust Halfspaces with Noise


May 15, 2020
Omar Montasser, Surbhi Goel, Ilias Diakonikolas, Nathan Srebro


  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

Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity


Mar 09, 2020
Pritish Kamath, Omar Montasser, Nathan Srebro


  Access Paper or Ask Questions

Dropout: Explicit Forms and Capacity Control


Mar 06, 2020
Raman Arora, Peter Bartlett, Poorya Mianjy, Nathan Srebro


  Access Paper or Ask Questions

Fair Learning with Private Demographic Data


Feb 26, 2020
Hussein Mozannar, Mesrob I. Ohannessian, Nathan Srebro


  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

Is Local SGD Better than Minibatch SGD?


Feb 18, 2020
Blake Woodworth, Kumar Kshitij Patel, Sebastian U. Stich, Zhen Dai, Brian Bullins, H. Brendan McMahan, Ohad Shamir, Nathan Srebro

* 29 pages 

  Access Paper or Ask Questions

Lower Bounds for Non-Convex Stochastic Optimization


Dec 05, 2019
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Nathan Srebro, Blake Woodworth


  Access Paper or Ask Questions

A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case


Oct 03, 2019
Greg Ongie, Rebecca Willett, Daniel Soudry, Nathan Srebro


  Access Paper or Ask Questions

Open Problem: The Oracle Complexity of Convex Optimization with Limited Memory


Jul 01, 2019
Blake Woodworth, Nathan Srebro

* 9 pages 

  Access Paper or Ask Questions

Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis


Jun 21, 2019
Ryan Rogers, Aaron Roth, Adam Smith, Nathan Srebro, Om Thakkar, Blake Woodworth


  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

Semi-Cyclic Stochastic Gradient Descent


Apr 23, 2019
Hubert Eichner, Tomer Koren, H. Brendan McMahan, Nathan Srebro, Kunal Talwar


  Access Paper or Ask Questions

The Complexity of Making the Gradient Small in Stochastic Convex Optimization


Feb 14, 2019
Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake Woodworth


  Access Paper or Ask Questions

How do infinite width bounded norm networks look in function space?


Feb 13, 2019
Pedro Savarese, Itay Evron, Daniel Soudry, Nathan Srebro


  Access Paper or Ask Questions