Picture for Ohad Shamir

Ohad Shamir

Open Problem: Anytime Convergence Rate of Gradient Descent

Add code
Jun 19, 2024
Viaarxiv icon

Depth Separation in Norm-Bounded Infinite-Width Neural Networks

Add code
Feb 13, 2024
Viaarxiv icon

Generalization in Kernel Regression Under Realistic Assumptions

Add code
Dec 26, 2023
Figure 1 for Generalization in Kernel Regression Under Realistic Assumptions
Figure 2 for Generalization in Kernel Regression Under Realistic Assumptions
Viaarxiv icon

An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization

Add code
Jul 10, 2023
Viaarxiv icon

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks

Add code
May 25, 2023
Viaarxiv icon

From Tempered to Benign Overfitting in ReLU Neural Networks

Add code
May 24, 2023
Figure 1 for From Tempered to Benign Overfitting in ReLU Neural Networks
Figure 2 for From Tempered to Benign Overfitting in ReLU Neural Networks
Figure 3 for From Tempered to Benign Overfitting in ReLU Neural Networks
Figure 4 for From Tempered to Benign Overfitting in ReLU Neural Networks
Viaarxiv icon

Deterministic Nonsmooth Nonconvex Optimization

Add code
Feb 16, 2023
Viaarxiv icon

On the Complexity of Finding Small Subgradients in Nonsmooth Optimization

Add code
Sep 21, 2022
Figure 1 for On the Complexity of Finding Small Subgradients in Nonsmooth Optimization
Viaarxiv icon

Reconstructing Training Data from Trained Neural Networks

Add code
Jun 15, 2022
Figure 1 for Reconstructing Training Data from Trained Neural Networks
Figure 2 for Reconstructing Training Data from Trained Neural Networks
Figure 3 for Reconstructing Training Data from Trained Neural Networks
Figure 4 for Reconstructing Training Data from Trained Neural Networks
Viaarxiv icon

The Sample Complexity of One-Hidden-Layer Neural Networks

Add code
Feb 13, 2022
Figure 1 for The Sample Complexity of One-Hidden-Layer Neural Networks
Viaarxiv icon