← Authors

Gilad Yehudai

19 papers · 2019–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (23) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (6) 🀝 Dynamic Duo (11) πŸ’Ž Century Club (19) πŸ—ƒοΈ Keyword Collector (58) πŸ”₯ Unstoppable (7)

Conferences

NIPS (8) COLT (5) ICLR (2) ICML (2) AISTATS (1) ALT (1)

Top co-authors

Ohad Shamir (11) Gal Vardi (7) Eran Malach (2) Niv Haim (2) Amit Daniely (2) Mariano Schain (2) Shai Shalev-Schwartz (2) Michal Irani (2) Odelia Melamed (2) Ethan Fetaya (1)

Keywords

neural network (6) relu network (5) gradient descent (4) adversarial example (3) single neuron (2) implicit bia (2) representation learning (2) data reconstruction (2) adversarial robustness (2) function approximation (1) margin maximization (1) convex optimization (1) semi-definite programming (1) strong convexity (1) lottery ticket hypothesis (1) multiclass classification (1) relu activation (1) neural network optimization (1) deep neural network (1) convolutional neural network (1)

Papers

Logarithmic Width Suffices for Robust Memorization COLT 2025
Locally Optimal Descent for Dynamic Stepsize Scheduling AISTATS 2025
Quality over Quantity in Attention Layers: When Adding More Heads Hurts ICLR 2025
MALT Powers Up Adversarial Attacks NIPS 2024
RedEx: Beyond Fixed Representation Methods via Convex Optimization ALT 2024
Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses NIPS 2023
From Tempered to Benign Overfitting in ReLU Neural Networks NIPS 2023
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces NIPS 2023
Gradient Methods Provably Converge to Non-Robust Networks NIPS 2022
Width is Less Important than Depth in ReLU Neural Networks COLT 2022
On the Optimal Memorization Power of ReLU Neural Networks ICLR 2022
Reconstructing Training Data From Trained Neural Networks NIPS 2022
From Local Structures to Size Generalization in Graph Neural Networks ICML 2021
Learning a Single Neuron with Bias Using Gradient Descent NIPS 2021
The Connection Between Approximation, Depth Separation and Learnability in Neural Networks COLT 2021
The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks COLT 2021
Learning a Single Neuron with Gradient Methods COLT 2020
Proving the Lottery Ticket Hypothesis: Pruning is All You Need ICML 2020
On the Power and Limitations of Random Features for Understanding Neural Networks NIPS 2019