← Authors

Gal Vardi

29 papers · 2020–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (25) 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (5) 🀝 Dynamic Duo (11) πŸ”¬ Deep Specialist (15) πŸ† Keyword Champion (3) πŸ’Ž Century Club (29) ⚑ Prolific Year (8) πŸ”₯ Unstoppable (6) πŸ—ƒοΈ Keyword Collector (75)

Conferences

NIPS (15) ICLR (7) COLT (6) ALT (1)

Top co-authors

Ohad Shamir (11) Nathan Srebro (7) Gilad Yehudai (7) Spencer Frei (5) Nati Srebro (5) Amit Daniely (4) Michal Irani (2) Nirmit Joshi (2) Niv Haim (2) Wei Hu (2)

Keywords

relu network (12) neural network (10) implicit bia (5) gradient flow (5) learning theory (4) gradient descent (3) benign overfitting (3) adversarial robustness (3) margin maximization (3) kkt condition (2) depth separation (2) neural network optimization (2) adversarial example (2) implicit regularization (2) hardness result (2) data reconstruction (2) uniform convergence (1) ridge regression (1) multiclass classification (1) computational complexity (1)

Papers

A Theory of Learning with Autoregressive Chain of Thought COLT 2025
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks ICLR 2025
Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context ICLR 2025
Provable Tempered Overfitting of Minimal Nets and Typical Nets NIPS 2024
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality NIPS 2024
An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression ICLR 2024
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data ICLR 2024
Noisy Interpolation Learning with Shallow Univariate ReLU Networks ICLR 2024
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization COLT 2023
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks NIPS 2023
Most Neural Networks Are Almost Learnable NIPS 2023
Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses NIPS 2023
Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy NIPS 2023
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces NIPS 2023
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data ICLR 2023
Implicit Regularization Towards Rank Minimization in ReLU Networks ALT 2023
On Margin Maximization in Linear and ReLU Networks NIPS 2022
Width is Less Important than Depth in ReLU Neural Networks COLT 2022
The Sample Complexity of One-Hidden-Layer Neural Networks NIPS 2022
On the Optimal Memorization Power of ReLU Neural Networks ICLR 2022
Gradient Methods Provably Converge to Non-Robust Networks NIPS 2022
Reconstructing Training Data From Trained Neural Networks NIPS 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NIPS 2022
Size and Depth Separation in Approximating Benign Functions with Neural Networks COLT 2021
Implicit Regularization in ReLU Networks with the Square Loss COLT 2021
From Local Pseudorandom Generators to Hardness of Learning COLT 2021
Learning a Single Neuron with Bias Using Gradient Descent NIPS 2021
Hardness of Learning Neural Networks with Natural Weights NIPS 2020
Neural Networks with Small Weights and Depth-Separation Barriers NIPS 2020