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 Amit Daniely

Asynchronous Stochastic Optimization Robust to Arbitrary Delays


Jun 22, 2021
Alon Cohen, Amit Daniely, Yoel Drori, Tomer Koren, Mariano Schain


  Access Paper or Ask Questions

An Exact Poly-Time Membership-Queries Algorithm for Extraction a three-Layer ReLU Network


May 20, 2021
Amit Daniely, Elad Granot


  Access Paper or Ask Questions

From Local Pseudorandom Generators to Hardness of Learning


Jan 20, 2021
Amit Daniely, Gal Vardi


  Access Paper or Ask Questions

Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations


Oct 28, 2020
Amit Daniely, Hadas Schacham


  Access Paper or Ask Questions

Hardness of Learning Neural Networks with Natural Weights


Jun 05, 2020
Amit Daniely, Gal Vardi


  Access Paper or Ask Questions

Memorizing Gaussians with no over-parameterizaion via gradient decent on neural networks


Mar 28, 2020
Amit Daniely


  Access Paper or Ask Questions

Learning Parities with Neural Networks


Feb 18, 2020
Amit Daniely, Eran Malach


  Access Paper or Ask Questions

On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions


Feb 09, 2020
Yossi Arjevani, Amit Daniely, Stefanie Jegelka, Hongzhou Lin


  Access Paper or Ask Questions

Neural Networks Learning and Memorization with (almost) no Over-Parameterization


Nov 22, 2019
Amit Daniely


  Access Paper or Ask Questions

Generalization Bounds for Neural Networks via Approximate Description Length


Oct 13, 2019
Amit Daniely, Elad Granot

* To appear in NeurIPS 

  Access Paper or Ask Questions

The Implicit Bias of Depth: How Incremental Learning Drives Generalization


Sep 26, 2019
Daniel Gissin, Shai Shalev-Shwartz, Amit Daniely

* 24 pages, 7 figures 

  Access Paper or Ask Questions

On the Optimality of Trees Generated by ID3


Jul 11, 2019
Alon Brutzkus, Amit Daniely, Eran Malach


  Access Paper or Ask Questions

ID3 Learns Juntas for Smoothed Product Distributions


Jun 20, 2019
Alon Brutzkus, Amit Daniely, Eran Malach


  Access Paper or Ask Questions

Competitive ratio versus regret minimization: achieving the best of both worlds


Apr 07, 2019
Amit Daniely, Yishay Mansour


  Access Paper or Ask Questions

Learning without Interaction Requires Separation


Sep 24, 2018
Amit Daniely, Vitaly Feldman


  Access Paper or Ask Questions

Learning with Rules


May 22, 2018
Deborah Cohen, Amit Daniely, Amir Globerson, Gal Elidan


  Access Paper or Ask Questions

Planning and Learning with Stochastic Action Sets


May 07, 2018
Craig Boutilier, Alon Cohen, Amit Daniely, Avinatan Hassidim, Yishay Mansour, Ofer Meshi, Martin Mladenov, Dale Schuurmans


  Access Paper or Ask Questions

Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity


May 19, 2017
Amit Daniely, Roy Frostig, Yoram Singer


  Access Paper or Ask Questions

SGD Learns the Conjugate Kernel Class of the Network


May 19, 2017
Amit Daniely


  Access Paper or Ask Questions

Random Features for Compositional Kernels


Mar 22, 2017
Amit Daniely, Roy Frostig, Vineet Gupta, Yoram Singer


  Access Paper or Ask Questions

Depth Separation for Neural Networks


Feb 27, 2017
Amit Daniely


  Access Paper or Ask Questions

Behavior-Based Machine-Learning: A Hybrid Approach for Predicting Human Decision Making


Nov 30, 2016
Gali Noti, Effi Levi, Yoav Kolumbus, Amit Daniely


  Access Paper or Ask Questions

Sketching and Neural Networks


Apr 19, 2016
Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar


  Access Paper or Ask Questions

Complexity Theoretic Limitations on Learning Halfspaces


Mar 13, 2016
Amit Daniely


  Access Paper or Ask Questions

Distribution Free Learning with Local Queries


Mar 11, 2016
Galit Bary-Weisberg, Amit Daniely, Shai Shalev-Shwartz


  Access Paper or Ask Questions

A PTAS for Agnostically Learning Halfspaces


Jun 25, 2015
Amit Daniely


  Access Paper or Ask Questions

Strongly Adaptive Online Learning


Jun 19, 2015
Amit Daniely, Alon Gonen, Shai Shalev-Shwartz


  Access Paper or Ask Questions

Multiclass learnability and the ERM principle


Nov 24, 2014
Amit Daniely, Sivan Sabato, Shai Ben-David, Shai Shalev-Shwartz

* Journal of Machine Learning Research, 16(Jul):1275-1304, 2015 

  Access Paper or Ask Questions

Complexity theoretic limitations on learning DNF's


Nov 04, 2014
Amit Daniely, Shai Shalev-Shwatz

* arXiv admin note: substantial text overlap with arXiv:1311.2272 

  Access Paper or Ask Questions

Learning Economic Parameters from Revealed Preferences


Jul 30, 2014
Maria-Florina Balcan, Amit Daniely, Ruta Mehta, Ruth Urner, Vijay V. Vazirani


  Access Paper or Ask Questions