ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Gal Vardi

Gal Vardi

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 4:51 AM AMS

16

papers

406

total citations

papers (16)

Reconstructing Training Data From Trained Neural Networks

NEURIPS 2022arXiv

On Margin Maximization in Linear and ReLU Networks

NEURIPS 2022arXiv

Gradient Methods Provably Converge to Non-Robust Networks

NEURIPS 2022arXiv

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses

NEURIPS 2023arXiv

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

NEURIPS 2022arXiv

Hardness of Learning Neural Networks with Natural Weights

NEURIPS 2020arXiv

Learning a Single Neuron with Bias Using Gradient Descent

NEURIPS 2021arXiv

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

NEURIPS 2023arXiv

Neural Networks with Small Weights and Depth-Separation Barriers

NEURIPS 2020arXiv

The Sample Complexity of One-Hidden-Layer Neural Networks

NEURIPS 2022arXiv

Noisy Interpolation Learning with Shallow Univariate ReLU Networks

Benign Overfitting in Single-Head Attention

NEURIPS 2025arXiv

Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy

NEURIPS 2023arXiv

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

NEURIPS 2023arXiv

Transformers are almost optimal metalearners for linear classification

NEURIPS 2025arXiv

Most Neural Networks Are Almost Learnable

NEURIPS 2023arXiv