Itay Safran

According to our database, Itay Safran authored at least 14 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Provable Privacy Attacks on Trained Shallow Neural Networks.

Guy Smorodinsky, Gal Vardi, Itay Safran

CoRR, 2024

Depth Separations in Neural Networks: Separating the Dimension from the Accuracy.

Itay Safran, Daniel Reichman, Paul Valiant

CoRR, 2024

How Many Neurons Does it Take to Approximate the Maximum?

Itay Safran, Daniel Reichman, Paul Valiant

Proceedings of the 2024 ACM-SIAM Symposium on Discrete Algorithms, 2024

2022

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

Itay Safran, Gal Vardi, Jason D. Lee

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Optimization-Based Separations for Neural Networks.

Itay Safran, Jason D. Lee

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

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

Itay Safran, Ohad Shamir

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

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

Itay Safran, Gilad Yehudai, Ohad Shamir

Proceedings of the Conference on Learning Theory, 2021

2020

How Good is SGD with Random Shuffling?

Itay Safran, Ohad Shamir

Proceedings of the Conference on Learning Theory, 2020

2019

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

Adi Shamir, Itay Safran, Eyal Ronen, Orr Dunkelman

CoRR, 2019

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

Itay Safran, Ronen Eldan, Ohad Shamir

Proceedings of the Conference on Learning Theory, 2019

2018

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

Itay Safran, Ohad Shamir

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks.

Itay Safran, Ohad Shamir

Proceedings of the 34th International Conference on Machine Learning, 2017

2016

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

Itay Safran, Ohad Shamir

CoRR, 2016

On the Quality of the Initial Basin in Overspecified Neural Networks.

Itay Safran, Ohad Shamir

Proceedings of the 33nd International Conference on Machine Learning, 2016