Portrait of Audrey Durand

Audrey Durand

Associate Academic Member
Canada CIFAR AI Chair
Associate professor, Université Laval, Department of Computer Science and Software Engineering
Research Topics
AI for Science
Online Learning
Reinforcement Learning
Website
Google Scholar
LinkedIn

Biography

Audrey Durand is an assistant professor in the Department of Computer Science and Software Engineering and in the Department of Electrical and Computer Engineering at Université Laval.

She specializes in algorithms that learn through interaction with their environment using reinforcement learning, and is particularly interested in leveraging these approaches in health-related applications.

Current Students

Julien Armand
Master's Research - Université Laval
Yohaï-Eliel Berreby
PhD - McGill University
Website
Github
Google Scholar
Baptiste Bonin
Master's Research - Université Laval
Hugo Delhaye
Master's Research - Université de Montréal
Principal supervisor :
Lune Bellec
Maxime Heuillet
PhD - Université Laval
Bruno Joyal
Master's Research - Université Laval
Alexandre Larouche
PhD - Université Laval
Github
Google Scholar
Randy Lefebvre
PhD - Université Laval
Hadi Moazen
PhD - Université Laval
Caro Strickland
Postdoctorate - Université Laval
Website
Github
Google Scholar

Publications

Streaming kernel regression with provably adaptive mean, variance, and regularization
Audrey Durand
Odalric-Ambrym Maillard
Joelle Pineau
We consider the problem of streaming kernel regression, when the observations arrive sequentially and the goal is to recover the underlying … (see more)mean function, assumed to belong to an RKHS. The variance of the noise is not assumed to be known. In this context, we tackle the problem of tuning the regularization parameter adaptively at each time step, while maintaining tight confidence bounds estimates on the value of the mean function at each point. To this end, we first generalize existing results for finite-dimensional linear regression with fixed regularization and known variance to the kernel setup with a regularization parameter allowed to be a measurable function of past observations. Then, using appropriate self-normalized inequalities we build upper and lower bound estimates for the variance, leading to Bersntein-like concentration bounds. The later is used in order to define the adaptive regularization. The bounds resulting from our technique are valid uniformly over all observation points and all time steps, and are compared against the literature with numerical experiments. Finally, the potential of these tools is illustrated by an application to kernelized bandits, where we revisit the Kernel UCB and Kernel Thompson Sampling procedures, and show the benefits of the novel adaptive kernel tuning strategy.
2017-12-31
Journal of Machine Learning Research (published)
arxiv.org
arxiv.org
Temporal Regularization for Markov Decision Process
Pierre Thodoroff
Audrey Durand
Joelle Pineau
Doina Precup
Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensiona… (see more)l domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularization techniques focus on spatial (perceptual) regularization. Yet in reinforcement learning, due to the nature of the Bellman equation, there is an opportunity to also exploit temporal regularization based on smoothness in value estimates over trajectories. This paper explores a class of methods for temporal regularization. We formally characterize the bias induced by this technique using Markov chain concepts. We illustrate the various characteristics of temporal regularization via a sequence of simple discrete and continuous MDPs, and show that the technique provides improvement even in high-dimensional Atari games.
2017-12-31
Advances in Neural Information Processing Systems 31 (NeurIPS 2018) (published)
dblp.uni-trier.de