Marc Jourdan

Marc Jourdan

Post-Doctoral Researcher

TML lab

EPFL

Biography

I am a postdoctoral researcher in the Theory of Machine Learning lab at EPFL, working with Nicolas Flammarion to deepen the theoretical understanding of Large Language Models and their advanced learning capabilities. My research interests include multi-armed bandits, reinforcement learning, online learning, imitation learning, optimization, statistics, and machine learning in general. I focus on developing theoretically well-founded and practically applicable algorithms.

I received my PhD in Computer Science from the University of Lille, where I worked under the direction of Emilie Kaufmann and Rémy Degenne in the Inria Scool team. My PhD research focused on pure exploration problems for stochastic multi-armed bandits. My thesis endeavored to establish the Top Two approach as a principled methodology offering nearly optimal theoretical guarantees alongside state-of-the-art empirical performance. My thesis touched upon various aspects of bandit theory: parametric and non-parametric classes of distributions, structural assumptions on their means, and different identification problems. During my PhD, I had the opportunity to visit Nicolò Cesa-Bianchi at the University of Milan in the Laboratory for Artificial Intelligence and Learning Algorithms for three months, where I worked on adversarial regret minimization for contextual linear bandits.

Before my PhD, I graduated from Ecole Polytechnique and ETH Zurich. I conducted my Master’s thesis in the Learning & Adaptive Systems group of Andreas Krause, where I studied pure exploration for combinatorial bandits with semi-bandit feedback.

Interests
  • Theory of Large Language Models
  • Multi-Armed Bandits
  • Online Learning
  • Statistics
  • Machine Learning
Education
  • PhD in Computer Science, 2021-2024

    Scool (Inria) / CRIStAL (CNRS) / Univ. Lille

  • MSc ETH in Data Science, 2018-2020

    ETH Zurich

  • Diplôme d'Ingénieur (MSc), 2015-2018

    École Polytechnique

Publications

Experience

 
 
 
 
 
Theory of Machine Learning lab (EPFL)
Post-doctoral Researcher
Oct 2024 – Present Lausanne, Switzerland
Post-doctoral researcher at EPFL, working with Dr. Nicolas Flammarion.
 
 
 
 
 
3-months research visit to collaborate with Prof. Dr. Nicolò Cesa-Bianchi.
 
 
 
 
 
Scool (Inria Lille)
Research Intern
Mar 2021 – Jul 2021 Villeneuve d'Ascq, France
Bandit identification with continuous answers under the supervision of Dr. Rémy Degenne.
 
 
 
 
 
Learning and Adaptive Systems (ETH Zurich)
Master’s Thesis
Apr 2020 – Sep 2020 Zurich, Switzerland
Pure exploration for combinatorial semi-bandits in the group of Prof. Dr. Andreas Krause.
 
 
 
 
 
AMAG Leasing
Part time Data Scientist
Feb 2019 – Jul 2019 Zurich, Switzerland
Created a recommender system for customers and developed models to predict churn and customer recovery.
 
 
 
 
 
IBM Singapore Lab
Research Intern
Apr 2018 – Aug 2018 Singapore
Characterized entities in the Bitcoin blockchain and developed a probabilistic model of its evolution.
 
 
 
 
 
STMicroelectronics
Research Intern
Jun 2017 – Aug 2017 Crolles, France
Implemented a quantized convolutional neural network in order to synthesize it on a electronic chip.

Contact