Professional headshot

Yonatan Slutzky

Email: slutzky1 at tau dot ac dot il

Hi there! I'm Yonatan (Yoni) Slutzky, a direct-track Ph.D. candidate in the School of Computer Science and AI at Tel Aviv University, fortunately advised by Prof. Nadav Cohen. Previously, I graduated summa cum laude with a B.Sc. in Computer Science, Statistics and Operations Research from Tel Aviv University.

My work revolves around the theoretical foundations of deep learning, with the goal of uncovering principles that can improve practical performance. Recently, I have been focused on the intersection of deep learning with reinforcement learning and control theory.

Other interests of mine include strength sports and pro wrestling.

Publications
* equal contribution

Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study

Yotam Alexander, Yonatan Slutzky, Yuval Ran-Milo, Nadav Cohen

arXiv preprint arXiv:2506.03931, 2025

Matrix Factorization
Simplicity Bias
Implicit Bias

Mamba Knockout for Unraveling Factual Information Flow

Nir Endy*, Idan Daniel Grosbard*, Yuval Ran-Milo*,Yonatan Slutzky*, Itay Tshuva, Raja Giryes

Association for Computational Linguistics (ACL), 2025

State Space Models
Linear Attention
Explainability

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels

Yonatan Slutzky*, Yotam Alexander*, Noam Razin, Nadav Cohen

arXiv preprint arXiv:2410.10473, 2024

State Space Models
Implicit Bias
Adversarial Machine Learning
Teaching
Tel Aviv University

Teaching Assistant

Intro to Machine Learning 0368-3235

Spring 2025

Teaching Assistant

Foundations of Deep Learning 0368-3080

Spring 2024

Teaching Assistant

Workshop on Deep Learning 0368-3538

Spring 2024, Spring 2025

Teaching Assistant

Statistical Learning 0365-4063

Fall 2023

© 2025 Yonatan Slutzky. All rights reserved.

Last updated: June 2025