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 Edgar Dobriban

PAC Prediction Sets Under Covariate Shift


Jun 17, 2021
Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani


  Access Paper or Ask Questions

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition


Mar 17, 2021
Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma


  Access Paper or Ask Questions

Sparse sketches with small inversion bias


Nov 21, 2020
Michał Dereziński, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney


  Access Paper or Ask Questions

What causes the test error? Going beyond bias-variance via ANOVA


Oct 11, 2020
Licong Lin, Edgar Dobriban


  Access Paper or Ask Questions

DeltaGrad: Rapid retraining of machine learning models


Jun 30, 2020
Yinjun Wu, Edgar Dobriban, Susan B. Davidson

* published in ICML 2020 

  Access Paper or Ask Questions

Provable tradeoffs in adversarially robust classification


Jun 09, 2020
Edgar Dobriban, Hamed Hassani, David Hong, Alexander Robey

* 27 pages, 4 figures 

  Access Paper or Ask Questions

The Implicit Regularization of Stochastic Gradient Flow for Least Squares


Mar 17, 2020
Alnur Ali, Edgar Dobriban, Ryan J. Tibshirani


  Access Paper or Ask Questions

Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods


Feb 21, 2020
Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci


  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

Invariance reduces Variance: Understanding Data Augmentation in Deep Learning and Beyond


Jul 25, 2019
Shuxiao Chen, Edgar Dobriban, Jane H Lee


  Access Paper or Ask Questions

One-shot distributed ridge regression in high dimensions


Mar 22, 2019
Edgar Dobriban, Yue Sheng


  Access Paper or Ask Questions

A New Theory for Sketching in Linear Regression


Oct 14, 2018
Edgar Dobriban, Sifan Liu


  Access Paper or Ask Questions

Distributed linear regression by averaging


Sep 30, 2018
Edgar Dobriban, Yue Sheng


  Access Paper or Ask Questions

High-Dimensional Asymptotics of Prediction: Ridge Regression and Classification


Nov 04, 2015
Edgar Dobriban, Stefan Wager

* Added a section on prediction versus estimation for ridge regression. Rewrote introduction. Other results unchanged 

  Access Paper or Ask Questions