I am a Ph.D. student in Electrical Engineering at KTH Royal Institute of Technology in Stockholm, Sweden, co-advised by Mikael Skoglund and Tobias Oechtering. My doctoral research is supported by the WASP Graduate School, where I am pursuing the joint curriculum in Artificial Intelligence and Autonomous Systems.
Before starting my Ph.D., I completed a double Master’s degree in Applied and Computational Mathematics from KTH and École Polytechnique de Louvain, and a Bachelor’s degree in Applied Mathematics and Electrical Engineering from École Polytechnique de Louvain.
In 2024, I had the opportunity to work as a Visiting Student Researcher at Stanford University under the supervision of Professor Benjamin Van Roy.
I am currenly doing a research internship at Lynx Asset Managementy, applying reinforcement learning to the problem of optimal trade execution.
My research interests lie at the intersection of reinforcement learning and information theory. Specifically, I study the performance of the Thompson Sampling algorithm in bandit problems.
I welcome discussions with anyone interested in topics in information theory and machine learning. Feel free to connect!
Publications (Chronological)
Amaury Gouverneur, Tobias J. Oechtering, and Mikael Skoglund, Refined PAC-Bayes Bounds for Offline Bandits
Accepted at ISIT 2025 | pdf
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund, An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits
Presented at NeurIPS 2024 Workshop on "Bayesian Decision-making and Uncertainty" | pdf
Raghav Bongole, Amaury Gouverneur, Tobias J. Oechtering, and Mikael Skoglund, Information-Theoretic Minimax Regret Bounds for Reinforcement Learning Problems
Submitted to ITW 2025 | pdf
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund, An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces
Presented at ICASSP 2025 | pdf
Raghav Bongole, Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund, Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality
Presented at ICASSP 2025 | pdf
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund, Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems
Presented at ICML 2024 (FoRLaC Workshop) | arXiv | pdf
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund, Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards
Presented at ISIT 2023 | arXiv | pdf | conference pdf
Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, and Mikael Skoglund, An Information-Theoretic Analysis of Bayesian Reinforcement Learning
Presented at Allerton 2022 | arXiv | pdf | conference pdf
Antoine Aspeel, Amaury Gouverneur, Raphaël M. Jungers, and Benoit Macq, Optimal intermittent particle filter
Published in IEEE Transactions on Signal Processing 2022 | arXiv | pdf | journal pdf
Amaury Gouverneur, Optimal measurement times for particle filtering and its application in mobile tumor tracking
Master Thesis 2022, Prom.: Benoit Macq | dial | pdf
Antoine Aspeel, Amaury Gouverneur, Raphaël M. Jungers, and Benoit Macq, Optimal measurement budget allocation for particle filtering
Presented at ICIP 2020 arXiv | pdf | conference pdf
Teaching
Project in Multimedia Processing and Analysis, EQ2445 at KTH - 2024
Machine Learning and Data Science, EQ2415 at KTH - 2024
Pattern Recognition and Machine Learning, EQ2341 at KTH - 2020-2024
Deep Neural Networks, EP232U at KTH - Spring 2022
Service
Reviewing service for EUSIPCO (2022-2023), ICML 2024, ICASSP 2025, ICLR 2025
WASP Cluster leader for Mathematical Foundations of AI other than ML (2020-2024)
WASP Cluster leader for Sequential Decision-Making and Reinforcement Learning (current)
Bachelor Thesis Supervision:
- Reza Qorbani, Kevin Pettersson - Investigation of Information-Theoretic Bounds on Generalization Error
- Edwin Östlund, Aron Malmborg - Fine-Tuning a GPT Model for Human-Like Chess Playing
- Tim Persson, Markus Palmheden - Researching GPT Model for Human-Like Chess Playing
Master Thesis Supervision
- Zhen Tian: Anomaly Detection in Application Logs
- Guangze Shi: Privacy Leaks from Deep Linear Networks
- Daniel Pérez: Improving Recommender Engines for Video Streaming Platforms with RNNs