Itay Safran

发表

On the Quality of the Initial Basin in Overspecified Neural Networks

Ohad Shamir, Itay Safran, O. Shamir, 2015, ICML.

How Good is SGD with Random Shuffling? pdf

Ohad Shamir, Itay Safran, O. Shamir, 2019, COLT.

Spurious Local Minima are Common in Two-Layer ReLU Neural Networks pdf

Ohad Shamir, Itay Safran, O. Shamir, 2017, ICML.

On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias

Jason D. Lee, Itay Safran, Gal Vardi, 2022, ArXiv.

Depth Separations in Neural Networks: What is Actually Being Separated?

O. Shamir, Ronen Eldan, Itay Safran, 2021, Constructive approximation.

Depth Separations in Neural Networks: What is Actually Being Separated? pdf

Ohad Shamir, Ronen Eldan, Itay Safran, 2019, Constructive Approximation.

Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks

Ohad Shamir, Itay Safran, O. Shamir, 2016, ICML.

On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias

Jason D. Lee, Itay Safran, Gal Vardi, 2022, NeurIPS.

The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks pdf

Gilad Yehudai, Ohad Shamir, Itay Safran, 2020, COLT.

Optimization-Based Separations for Neural Networks

Jason D. Lee, Itay Safran, 2021, COLT.

A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance pdf

Adi Shamir, Orr Dunkelman, Eyal Ronen, 2019, ArXiv.

Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems pdf

Ohad Shamir, Itay Safran, O. Shamir, 2021, NeurIPS.

Depth Separation in ReLU Networks for Approximating Smooth Non-Linear Functions pdf

Ohad Shamir, Itay Safran, O. Shamir, 2016, ArXiv.

How Many Neurons Does it Take to Approximate the Maximum?

Paul Valiant, Itay Safran, Daniel Reichman, 2023, ArXiv.

Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks

Itay Safran, Ohad Shamir, 2016, ICML.