Inbar Seroussi

According to our database, Inbar Seroussi authored at least 16 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks.

Donald Flynn, Hadas Yaron Goldhirsh, Jonathan P. Keating, Inbar Seroussi

CoRR, May, 2026

2025

Exact Dynamics of Multi-class Stochastic Gradient Descent.

Elizabeth Collins-Woodfin, Inbar Seroussi

CoRR, October, 2025

Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models.

Shai Zucker, Xiong Wang, Fei Lu, Inbar Seroussi

CoRR, October, 2025

A Geometric Unification of Generative AI with Manifold-Probabilistic Projection Models.

Leah Bar, Liron Mor-Yosef, Shai Zucker, Neta Shoham, Inbar Seroussi, Nir A. Sochen

CoRR, October, 2025

Better Rates for Private Linear Regression in the Proportional Regime via Aggressive Clipping.

Simone Bombari, Inbar Seroussi, Marco Mondelli

CoRR, May, 2025

Applications of Statistical Field Theory in Deep Learning.

Zohar Ringel, Noa Rubin, Edo Mor, Moritz Helias, Inbar Seroussi

CoRR, February, 2025

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning.

Noa Rubin, Kirsten Fischer, Javed Lindner, David Dahmen, Inbar Seroussi, Zohar Ringel, Michael Krämer, Moritz Helias

CoRR, February, 2025

From Kernels to Features: A Multi-Scale Adaptive Theory of Feature Learning.

Noa Rubin, Kirsten Fischer, Javed Lindner, Inbar Seroussi, Zohar Ringel, Michael Krämer, Moritz Helias

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Spectral-bias and kernel-task alignment in physically informed neural networks.

Inbar Seroussi, Asaf Miron, Zohar Ringel

Mach. Learn. Sci. Technol., 2024

The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms.

Elizabeth Collins-Woodfin, Inbar Seroussi, Begoña García Malaxechebarría, Andrew W. Mackenzie, Elliot Paquette, Courtney Paquette

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Grokking as a First Order Phase Transition in Two Layer Networks.

Noa Rubin, Inbar Seroussi, Zohar Ringel

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Droplets of Good Representations: Grokking as a First Order Phase Transition in Two Layer Networks.

Noa Rubin, Inbar Seroussi, Zohar Ringel

CoRR, 2023

Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models.

Elizabeth Collins-Woodfin, Courtney Paquette, Elliot Paquette, Inbar Seroussi

CoRR, 2023

Speed Limits for Deep Learning.

Inbar Seroussi, Alexander A. Alemi, Moritz Helias, Zohar Ringel

CoRR, 2023

2022

Lower Bounds on the Generalization Error of Nonlinear Learning Models.

Inbar Seroussi, Ofer Zeitouni

IEEE Trans. Inf. Theory, 2022

2021

Separation of scales and a thermodynamic description of feature learning in some CNNs.

Inbar Seroussi, Zohar Ringel

CoRR, 2021