Gon Buzaglo

PhD student | Computer Science | Princeton University

I'm a second-year PhD student at Princeton, where I have the privilege of being advised by Prof. Elad Hazan and supported by the Gordon Wu Fellowship.

Before my PhD, I had the pleasure of completing my master’s with Prof. Daniel Soudry, collaborating with Prof. Nathan Srebro, and interning with Prof. Michal Irani as an undergraduate.

I help to organize the ALG-ML seminar here at Princeton.

email: gon dot buzaglo at gmail dot com

Research

Preprints:

The Hidden Game Problem

Gon Buzaglo, Noah Golowich and Elad Hazan.

Publications:

A New Approach to Controlling Linear Dynamical Systems

Anand Brahmbhatt, Gon Buzaglo, Sofiia Druchyna and Elad Hazan (authors listed alphabetically). ICLR 2026.

Efficient Spectral Control of Partially Observed Linear Dynamical Systems

Anand Brahmbhatt, Gon Buzaglo, Sofiia Druchyna and Elad Hazan (authors listed alphabetically). NeurIPS 2025.

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers

Gon Buzaglo*, Itamar Harel*, Mor Shpigel-Nacson*, Alon Brutzkus, Nathan Srebro and Daniel Soudry. ICML 2024 (spotlight).

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses

Gon Buzaglo*, Niv Haim*, Gilad Yehudai, Gal Vardi, Yakir Oz, Yaniv Nikankin and Michal Irani. NeurIPS 2023.

Continual Learning in Linear Classification on Separable Data

Itay Evron, Edward Moroshko, Gon Buzaglo, Maroun Khriesh, Badea Marjieh, Nathan Srebro and Daniel Soudry. ICML 2023.

Teaching

COS 511 (Spring 2026): Theoretical Machine Learning @ Princeton

Instructor: Prof. Elad Hazan

COS 514 (Fall 2025): Fundamentals of Deep Learning @ Princeton

Instructor: Prof. Sanjeev Arora

Short Bio

2024 - 2029 | PhD in Computer Science | Princeton University
2023 - 2024 | M.Sc. in Electrical and Computer Engineering | Technion
2020 - 2024 | B.Sc. in Computer Science and Physics | Technion

Page updated

Google Sites

Report abuse