collaborators

6 papers

cs.LG2026

Limitations of SGD for Multi-Index Models Beyond Statistical Queries

Daniel Barzilai, Ohad Shamir

Understanding the limitations of gradient methods, and stochastic gradient descent (SGD) in particular, is a central challenge in learning theory. To that end, a commonly used tool…

stat.ML2026

When Models Don't Collapse: On the Consistency of Iterative MLE

Daniel Barzilai, Ohad Shamir

The widespread use of generative models has created a feedback loop, in which each generation of models is trained on data partially produced by its predecessors. This process has…

cs.LG2026

When Is Compositional Reasoning Learnable from Verifiable Rewards?

Daniel Barzilai, Yotam Wolf, Ronen Basri

The emergence of compositional reasoning in large language models through reinforcement learning with verifiable rewards (RLVR) has been a key driver of recent empirical successes.…

cs.LG2025

Beyond Benign Overfitting in Nadaraya-Watson Interpolators

Daniel Barzilai, Guy Kornowski, Ohad Shamir

In recent years, there has been much interest in understanding the generalization behavior of interpolating predictors, which overfit on noisy training data. Whereas standard analy…

math.PR2025

Simple Relative Deviation Bounds for Covariance and Gram Matrices

Daniel Barzilai, Ohad Shamir

We provide non-asymptotic, relative deviation bounds for the eigenvalues of empirical covariance and Gram matrices in general settings. Unlike typical uniform bounds, which may fai…

cs.LG2025

Querying Kernel Methods Suffices for Reconstructing their Training Data

Daniel Barzilai, Yuval Margalit, Eitan Gronich +3

Over-parameterized models have raised concerns about their potential to memorize training data, even when achieving strong generalization. The privacy implications of such memoriza…