Marco Jiralerspong

Hi! I'm a third-year PhD student in computer science (fast-tracked from masters) at Université de Montréal/Mila supervised by Gauthier Gidel and supported by NSERC.

Previously, I did my undergrad at McGill where I majored in computer science with minors in mathematics and economics. I also interned as a software engineer at Google, Amazon Robotics and Squarepoint Capital.

I am currently working on soft variants of reinforcement learning and potential applications to multi-agent problems. However, any topic that bridges computer science, economics and mathematics will be of interest!

Google Scholar Github Twitter

News

Jan 2026 Our paper "Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning" was accepted at ICLR 2026.

Dec 2026 Released a preliminary version of Modrax, a modular library for RL in Jax using NNX.

Aug 2025 Passed my Predoc 3 (proposal) exam!

Apr 2025 Received the NSERC Postgraduate Scholarship – Doctoral (PGS D).

Selected Publications

ICLR 2026 [Github]

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

Marco Jiralerspong, Esther Derman, Danilo Vucetic, Nikolay Malkin, Bilun Sun, Tianyu Zhang, Pierre-Luc Bacon, Gauthier Gidel

ICLR 2024 [Github]

Expected Flow Networks in Stochastic Environments and Two-Player Zero-Sum Games

Marco Jiralerspong*, Bilun Sun*, Danilo Vucetic*, Tianyu Zhang, Yoshua Bengio, Gauthier Gidel, Nikolay Malkin

ICLR 2024 Spotlight

On the Stability of Iterative Retraining of Generative Models on their own Data

Quentin Bertrand, Joey Bose, Alexandre Duplessis, Marco Jiralerspong, Gauthier Gidel

NeurIPS 2023 [Github]

Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples

Marco Jiralerspong, Joey Bose, Ian Gemp, Chongli Qin, Yoram Bachrach, Gauthier Gidel

Awards

NSERC Postgraduate Scholarship – Doctoral (PGS D): $40,000/year

FRQNT Doctoral Scholarship: $25,000/year (declined)

Projects

Gale-Shapley Interactive Simulation | Interactive Simulation

An interactive, step-by-step, visualization of the Gale-Shapley algorithm in action for random preferences.

Python for Biologists | Github

An introductory Python course for biologists explaining how to get set up, the basic elements of the language and progressively harder exercises.