activity
20242026
collaborators

6 papers

cs.LG2026

Scale Dependent Data Duplication

Joshua Kazdan, Noam Levi, Rylan Schaeffer +6

Data duplication during pretraining can degrade generalization and lead to memorization, motivating aggressive deduplication pipelines. However, at web scale, it is unclear what co…

stat.ML2026

The Implicit Bias of Logit Regularization

Alon Beck, Yohai Bar Sinai, Noam Levi

Logit regularization, the addition of a convex penalty directly in logit space, is widely used in modern classifiers, with label smoothing as a prominent example. While such method…

cs.LG2025

Ascent Fails to Forget

Ioannis Mavrothalassitis, Pol Puigdemont, Noam Itzhak Levi +1

Contrary to common belief, we show that gradient ascent-based unconstrained optimization methods frequently fail to perform machine unlearning, a phenomenon we attribute to the inh…

stat.ML2024

A Simple Model of Inference Scaling Laws

Noam Levi

Neural scaling laws have garnered significant interest due to their ability to predict model performance as a function of increasing parameters, data, and compute. In this work, we…

stat.ML2024

Probing the Latent Hierarchical Structure of Data via Diffusion Models

Antonio Sclocchi, Alessandro Favero, Noam Itzhak Levi +1

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitati…

stat.ML2024

Grokking at the Edge of Linear Separability

Alon Beck, Noam Levi, Yohai Bar-Sinai

We investigate the phenomenon of grokking -- delayed generalization accompanied by non-monotonic test loss behavior -- in a simple binary logistic classification task, for which "m…