Daniel Barzilai

According to our database, Daniel Barzilai authored at least 9 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

When Is Compositional Reasoning Learnable from Verifiable Rewards?

Daniel Barzilai, Yotam Wolf, Ronen Basri

CoRR, February, 2026

Limitations of SGD for Multi-Index Models Beyond Statistical Queries.

Daniel Barzilai, Ohad Shamir

CoRR, February, 2026

2025

Querying Kernel Methods Suffices for Reconstructing their Training Data.

Daniel Barzilai, Yuval Margalit, Eitan Gronich, Gilad Yehudai, Meirav Galun, Ronen Basri

CoRR, May, 2025

Overfitting Regimes of Nadaraya-Watson Interpolators.

Daniel Barzilai, Guy Kornowski, Ohad Shamir

CoRR, February, 2025

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

Daniel Barzilai, Ohad Shamir

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024

Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum.

Amnon Geifman, Daniel Barzilai, Ronen Basri, Meirav Galun

Trans. Mach. Learn. Res., 2024

Simple Relative Deviation Bounds for Covariance and Gram Matrices.

Daniel Barzilai, Ohad Shamir

CoRR, 2024

Generalization in Kernel Regression Under Realistic Assumptions.

Daniel Barzilai, Ohad Shamir

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

A Kernel Perspective of Skip Connections in Convolutional Networks.

Daniel Barzilai, Amnon Geifman, Meirav Galun, Ronen Basri

Proceedings of the Eleventh International Conference on Learning Representations, 2023