Gilad Yehudai

Joan Bruna

CoRR, 2024

Reconstructing Training Data From Real World Models Trained with Transfer Learning.

[BibT_eX]

[DOI]

CoRR, 2024

When Can Transformers Count to n?

[BibT_eX]

[DOI]

CoRR, 2024

MALT Powers Up Adversarial Attacks.

[BibT_eX]

[DOI]

Odelia Melamed

Adi Shamir

CoRR, 2024

RedEx: Beyond Fixed Representation Methods via Convex Optimization.

[BibT_eX]

[DOI]

Amit Daniely

Mariano Schain

Proceedings of the International Conference on Algorithmic Learning Theory, 2024

2023

Locally Optimal Descent for Dynamic Stepsize Scheduling.

[BibT_eX]

[DOI]

CoRR, 2023

Reconstructing Training Data from Multiclass Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Data Manifolds.

[BibT_eX]

[DOI]

Odelia Melamed

CoRR, 2023

Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces.

[BibT_eX]

[DOI]

Odelia Melamed

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

From Tempered to Benign Overfitting in ReLU Neural Networks.

[BibT_eX]

[DOI]

Guy Kornowski

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Gradient Methods Provably Converge to Non-Robust Networks.

[BibT_eX]

[DOI]

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

Reconstructing Training Data From Trained Neural Networks.

[BibT_eX]

[DOI]

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

On the Optimal Memorization Power of ReLU Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Width is Less Important than Depth in ReLU Neural Networks.

[BibT_eX]

[DOI]

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

2021

Learning a Single Neuron with Bias Using Gradient Descent.

[BibT_eX]

[DOI]

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

From Local Structures to Size Generalization in Graph Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

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

[BibT_eX]

[DOI]

Itay Safran

Proceedings of the Conference on Learning Theory, 2021

The Connection Between Approximation, Depth Separation and Learnability in Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

On Size Generalization in Graph Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2020

Proving the Lottery Ticket Hypothesis: Pruning is All You Need.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Learning a Single Neuron with Gradient Methods.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2020

2019

On the Power and Limitations of Random Features for Understanding Neural Networks.

[BibT_eX]

[DOI]