Gal Vardi

ACM Trans. Comput. Log., January, 2024

Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks.

[BibT_eX]

[DOI]

Nikolaos Tsilivis

Julia Kempe

CoRR, 2024

Provable Tempered Overfitting of Minimal Nets and Typical Nets.

[BibT_eX]

[DOI]

CoRR, 2024

Benign Overfitting in Single-Head Attention.

[BibT_eX]

[DOI]

CoRR, 2024

Provable Privacy Attacks on Trained Shallow Neural Networks.

[BibT_eX]

[DOI]

Guy Smorodinsky

Itay Safran

CoRR, 2024

Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context.

[BibT_eX]

[DOI]

Spencer Frei

CoRR, 2024

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality.

[BibT_eX]

[DOI]

Marko Medvedev

Nathan Srebro

CoRR, 2024

Approaching Deep Learning through the Spectral Dynamics of Weights.

[BibT_eX]

[DOI]

CoRR, 2024

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

[BibT_eX]

[DOI]

CoRR, 2024

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Noisy Interpolation Learning with Shallow Univariate ReLU Networks.

[BibT_eX]

[DOI]

Nirmit Joshi

Nathan Srebro

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

On the Implicit Bias in Deep-Learning Algorithms.

[BibT_eX]

[DOI]

Commun. ACM, June, 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

Efficiently Learning Neural Networks: What Assumptions May Suffice?

[BibT_eX]

[DOI]

Nathan Srebro

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

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks.

[BibT_eX]

[DOI]

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

Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy.

[BibT_eX]

[DOI]

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

Most Neural Networks Are Almost Learnable.

[BibT_eX]

[DOI]

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

Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

Implicit Regularization Towards Rank Minimization in ReLU Networks.

[BibT_eX]

[DOI]

Nadav Timor

Proceedings of the International Conference on Algorithmic Learning Theory, 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

On Margin Maximization in Linear and ReLU Networks.

[BibT_eX]

[DOI]

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

The Sample Complexity of One-Hidden-Layer 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 Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias.

[BibT_eX]

[DOI]

Itay Safran

Jason D. Lee

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

Size and Depth Separation in Approximating Natural Functions with Neural Networks.

[BibT_eX]

[DOI]

CoRR, 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

Implicit Regularization in ReLU Networks with the Square Loss.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

Size and Depth Separation in Approximating Benign Functions with Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

From Local Pseudorandom Generators to Hardness of Learning.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

Neural Networks with Small Weights and Depth-Separation Barriers.

[BibT_eX]

[DOI]

Electron. Colloquium Comput. Complex., 2020

Hardness of Learning Neural Networks with Natural Weights.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Graph-Theoretic Problems from the Viewpoint of Formal Methods (כותר נוסף בעברית: בעיות בתורת הגרפים מנקודת המבט של אימות פורמלי).

[BibT_eX]

[DOI]

PhD thesis, 2019

Flow Logic.

[BibT_eX]

[DOI]

Log. Methods Comput. Sci., 2019

Multi-player flow games.

[BibT_eX]

[DOI]

Shibashis Guha

Auton. Agents Multi Agent Syst., 2019

2018

On relative and probabilistic finite counterability.

[BibT_eX]

[DOI]

Formal Methods Syst. Des., 2018

Spanning-Tree Games.

[BibT_eX]

[DOI]

Proceedings of the 43rd International Symposium on Mathematical Foundations of Computer Science, 2018

The Unfortunate-Flow Problem.

[BibT_eX]

[DOI]

Proceedings of the 45th International Colloquium on Automata, Languages, and Programming, 2018

2017

Flow Games.

[BibT_eX]

[DOI]

Moshe Y. Vardi

Proceedings of the 37th IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science, 2017

2016

Eulerian Paths with Regular Constraints.

[BibT_eX]

[DOI]