works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.LG2026

To Grok Grokking: Provable Grokking in Ridge Regression

Mingyue Xu, Gal Vardi, Itay Safran

The paper provides a theoretical analysis of grokting—delayed generalization after overfitting—in ridge regression, showing how gradient descent with weight decay leads to three ph…

cs.LG2026

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective

Guy Smorodinsky, Sveta Gimpleson, Itay Safran

We study the convergence dynamics of Gradient Descent (GD) in a minimal binary classification setting, consisting of a two-neuron ReLU network and two training instances. We prove…

cs.LG2026

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network

Abhigyan Dutta, Itay Safran, Paul Valiant

We study the approximation of the median of inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-…

cs.LG2026

A Depth Hierarchy for Computing the Maximum in ReLU Networks via Extremal Graph Theory

Itay Safran

We consider the problem of exact computation of the maximum function over real inputs using ReLU neural networks. We prove a depth hierarchy, wherein width $Ω\big(d^{1+\frac{1…

cs.LG2025

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks

Yehonatan Refael, Guy Smorodinsky, Ofir Lindenbaum +1

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the traini…

cs.LG2025

Provable Privacy Attacks on Trained Shallow Neural Networks

Guy Smorodinsky, Gal Vardi, Itay Safran

We study what provable privacy attacks can be shown on trained, 2-layer ReLU neural networks. We explore two types of attacks; data reconstruction attacks, and membership inference…