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 Niladri S. Chatterji

When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?


Feb 09, 2021
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett

* 97 pages 

  Access Paper or Ask Questions

When does gradient descent with logistic loss find interpolating two-layer networks?


Dec 04, 2020
Niladri S. Chatterji, Philip M. Long, Peter L. Bartlett

* 43 pages, 4 figures 

  Access Paper or Ask Questions

Finite-sample analysis of interpolating linear classifiers in the overparameterized regime


Apr 25, 2020
Niladri S. Chatterji, Philip M. Long


  Access Paper or Ask Questions

Oracle lower bounds for stochastic gradient sampling algorithms


Feb 01, 2020
Niladri S. Chatterji, Peter L. Bartlett, Philip M. Long

* 21 pages 

  Access Paper or Ask Questions

The intriguing role of module criticality in the generalization of deep networks


Dec 04, 2019
Niladri S. Chatterji, Behnam Neyshabur, Hanie Sedghi


  Access Paper or Ask Questions

OSOM: A Simultaneously Optimal Algorithm for Multi-Armed and Linear Contextual Bandits


Jun 11, 2019
Niladri S. Chatterji, Vidya Muthukumar, Peter L. Bartlett

* Updated acknowledgements 

  Access Paper or Ask Questions

Langevin Monte Carlo without Smoothness


May 30, 2019
Niladri S. Chatterji, Jelena Diakonikolas, Michael I. Jordan, Peter L. Bartlett


  Access Paper or Ask Questions

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting


Sep 07, 2018
Xiang Cheng, Niladri S. Chatterji, Yasin Abbasi-Yadkori, Peter L. Bartlett, Michael I. Jordan

* 37 Pages 

  Access Paper or Ask Questions

Online learning with kernel losses


Feb 27, 2018
Aldo Pacchiano, Niladri S. Chatterji, Peter L. Bartlett

* 40 pages, 4 figures 

  Access Paper or Ask Questions

On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo


Feb 15, 2018
Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan

* 37 pages; 4 figures 

  Access Paper or Ask Questions

Alternating minimization for dictionary learning with random initialization


Jan 30, 2018
Niladri S. Chatterji, Peter L. Bartlett

* To appear at NIPS 2017; typos corrected from the previous version 

  Access Paper or Ask Questions

Underdamped Langevin MCMC: A non-asymptotic analysis


Jan 26, 2018
Xiang Cheng, Niladri S. Chatterji, Peter L. Bartlett, Michael I. Jordan

* 23 pages; Correction to Corollary 7 

  Access Paper or Ask Questions