Portrait of Guillaume Rabusseau

Guillaume Rabusseau

Core Academic Member
Canada CIFAR AI Chair
Assistant Professor, Université de Montréal, Department of Computer Science and Operations Research
Research Topics
Deep Learning
Graph Neural Networks
Learning on Graphs
Machine Learning Theory
Probabilistic Models
Quantum Information Theory
Recommender Systems
Recurrent Neural Networks
Tensor Factorization

Biography

I have been an assistant professor at Mila – Quebec Artificial Intelligence Institute and in the Department of Computer Science and Operations Research (DIRO) at Université de Montréal (UdeM) since September 2018. I was awarded a Canada CIFAR AI Chair in March 2019. Before joining UdeM, I was a postdoctoral research fellow in the Reasoning and Learning Lab at McGill University, where I worked with Prakash Panangaden, Joelle Pineau and Doina Precup.

I obtained my PhD in 2016 from Aix-Marseille University (AMU) in France, where I worked in the Qarma team (Machine Learning and Multimedia) under the supervision of François Denis and Hachem Kadri. I also obtained my MSc in fundamental computer science and my BSc in computer science from AMU. I am interested in tensor methods for machine learning and in designing learning algorithms for structured data by leveraging linear and multilinear algebra (e.g., spectral methods).

Current Students

Postdoctorate - Université de Montréal
Collaborating Alumni - Université de Montréal
PhD - Université de Montréal
Co-supervisor :
Collaborating researcher - McGill University
Principal supervisor :
PhD - Université de Montréal
Postdoctorate - McGill University
Co-supervisor :
Research Intern - Polytechnique Montréal
Collaborating researcher - INRIA
Master's Research - Université de Montréal
Collaborating researcher - Université de Montréal
Co-supervisor :
PhD - Université de Montréal
Research Intern - Université de Montréal

Publications

Multitask Spectral Learning of Weighted Automata.
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces
We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional… (see more) embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based methods allows us to derive strong theoretical guarantees on the expected return of the reconstructed policy. Such guarantees are typically lacking in black-box models, but are very desirable in tasks requiring stability. We conduct several experiments on classic RL domains. The results confirm that the policies can be robustly embedded in a low-dimensional space while the embedded policy incurs almost no decrease in return.