Gal Vardi
31 papers · 2020–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (34) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π¬
Deep Specialist
(22)
π€
Dynamic Duo
(11)
π
Keyword Champion
(5)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
ποΈ
Keyword Collector
(111)
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(30)
Optimization & Theory Β· Machine Learning
(29)
Deep Learning
(21)
Architectures
(16)
Optimization & Theory Β· Deep Learning
(13)
Core Methods
(8)
Artificial Intelligence
(5)
Core AI
(5)
Application Areas
(2)
Learning Types Β· Machine Learning
(2)
Learning Types Β· Deep Learning
(2)
Computer Science
(1)
Mathematics & Optimization
(1)
Bayesian & Probabilistic
(1)
Foundations
(1)
Keywords
relu network
(14)
neural network
(10)
implicit bia
(8)
gradient flow
(6)
gradient descent
(6)
margin maximization
(5)
learning theory
(5)
benign overfitting
(4)
neural network optimization
(3)
adversarial robustness
(3)
implicit regularization
(3)
depth separation
(3)
function approximation
(2)
data reconstruction
(2)
pac learning
(2)
relu neural network
(2)
kkt condition
(2)
hardness result
(2)
vc dimension
(2)
kernel ridge regression
(2)
Papers
Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks
JMLR 2026
On the Hardness of Learning Regular Expressions
ALT 2026
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
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
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
NeurIPS 2024
Provable Tempered Overfitting of Minimal Nets and Typical Nets
NeurIPS 2024
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
NeurIPS 2023
Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization
COLT 2023
Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy
NeurIPS 2023
Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
NeurIPS 2023
Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data
ICLR 2023
Implicit Regularization Towards Rank Minimization in ReLU Networks
ALT 2023
Most Neural Networks Are Almost Learnable
NeurIPS 2023
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
NeurIPS 2023
Gradient Methods Provably Converge to Non-Robust Networks
NeurIPS 2022
On Margin Maximization in Linear and ReLU Networks
NeurIPS 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias
NeurIPS 2022
On the Optimal Memorization Power of ReLU Neural Networks
ICLR 2022
Reconstructing Training Data From Trained Neural Networks
NeurIPS 2022
The Sample Complexity of One-Hidden-Layer Neural Networks
NeurIPS 2022
Width is Less Important than Depth in ReLU Neural Networks
COLT 2022
From Local Pseudorandom Generators to Hardness of Learning
COLT 2021
Implicit Regularization in ReLU Networks with the Square Loss
COLT 2021
Learning a Single Neuron with Bias Using Gradient Descent
NeurIPS 2021
Size and Depth Separation in Approximating Benign Functions with Neural Networks
COLT 2021
Hardness of Learning Neural Networks with Natural Weights
NeurIPS 2020
Neural Networks with Small Weights and Depth-Separation Barriers
NeurIPS 2020