Hristo Papazov

Hristo Papazov

I am a fourth-year PhD student in the Theory of Machine Learning lab at EPFL🇨🇭, where I am fortunate to be advised by Nicolas Flammarion. My research focuses on uncovering the hidden algorithmic processes underlying structured data through discrete and gradient-based methods.

Before joining EPFL, I spent a year as a PhD student in the math department at MIT, working on discrete algorithms. Prior to that, I completed a bachelor’s degree in math at Princeton, where I worked under the supervision of Sasha Logunov and Assaf Naor.

For more information, consider my full CV.

Research Interests

Contact

Email: hristo.papazov@epfl.ch

Student Projects

For a list of currently available master’s projects, check out the TML lab page.

Selected Publications

For a full list of publications, please visit my Google Scholar page.

Exact Learning of Arithmetic with Differentiable Agents
Hristo Papazov, Francesco D'Angelo, Nicolas Flammarion
Workshop on Mathematical Reasoning and AI, NeurIPS, 2025
Learning Algorithms in the Limit
Hristo Papazov, Nicolas Flammarion
COLT, 2025
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
Hristo Papazov, Scott Pesme, Nicolas Flammarion
AISTATS, 2024
An Elliptic Adaptation of Ideas of Carleman and Domar from Complex Analysis Related to Levinson’s LogLog Theorem
Aleksandr Logunov, Hristo Papazov
Journal of Mathematical Physics, 2021