Portrait de Audrey Durand

Audrey Durand

Membre académique associé
audrey.durand@ift.ulaval.ca
Chaire en IA Canada-CIFAR
Professeure adjointe, Université Laval, Département d'informatique et de génie logiciel
Sujets de recherche
Apprentissage en ligne
Apprentissage par renforcement
IA pour la science
Site web
Google Scholar
LinkedIn

Biographie

Audrey Durand est professeure adjointe au Département d’informatique et de génie logiciel ainsi qu’au Département de génie électrique et de génie informatique de l’Université Laval. Elle se spécialise dans les algorithmes qui apprennent par l’interaction avec leur environnement, soit l’apprentissage par renforcement, et s’intéresse particulièrement à l’application de ces approches au domaine de la santé.

Étudiants actuels

Julien Armand
Maîtrise recherche - Université Laval
julien.armand@mila.quebec
Yohaï-Eliel Berreby
Doctorat - McGill
me@yberreby.com
Site web
Github
Google Scholar
Baptiste Bonin
Maîtrise recherche - Université Laval
baptiste.bonin@mila.quebec
Hugo Delhaye
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e :
Lune Bellec
hugo.delhaye@mila.quebec
Erinn Grigsby
Postdoctorat - UdeM
erinn.grigsby@mila.quebec
Site web
Github
Google Scholar
Maxime Heuillet
Doctorat - Université Laval
maxime.heuillet@mila.quebec
Bruno Joyal
Maîtrise recherche - Université Laval
bruno.joyal@mila.quebec
Alexandre Larouche
Doctorat - Université Laval
alexandre.larouche@mila.quebec
Github
Google Scholar
Randy Lefebvre
Doctorat - Université Laval
randy.lefebvre@mila.quebec
Hadi Moazen
Doctorat - Université Laval
hadi.moazen@mila.quebec
Caro Strickland
Postdoctorat - Université Laval
caro.strickland@mila.quebec
Site web
Github
Google Scholar

Publications

On-line Adaptative Curriculum Learning for GANs
Thang Doan
Joao Monteiro
Isabela Albuquerque
Bogdan Mazoure
Audrey Durand
Joelle Pineau
R Devon Hjelm
Generative Adversarial Networks (GANs) can successfully approximate a probability distribution and produce realistic samples. However, open … (voir plus)questions such as sufficient convergence conditions and mode collapse still persist. In this paper, we build on existing work in the area by proposing a novel framework for training the generator against an ensemble of discriminator networks, which can be seen as a one-student/multiple-teachers setting. We formalize this problem within the full-information adversarial bandit framework, where we evaluate the capability of an algorithm to select mixtures of discriminators for providing the generator with feedback during learning. To this end, we propose a reward function which reflects the progress made by the generator and dynamically update the mixture weights allocated to each discriminator. We also draw connections between our algorithm and stochastic optimization methods and then show that existing approaches using multiple discriminators in literature can be recovered from our framework. We argue that less expressive discriminators are smoother and have a general coarse grained view of the modes map, which enforces the generator to cover a wide portion of the data distribution support. On the other hand, highly expressive discriminators ensure samples quality. Finally, experimental results show that our approach improves samples quality and diversity over existing baselines by effectively learning a curriculum. These results also support the claim that weaker discriminators have higher entropy improving modes coverage. Keywords: multiple discriminators, curriculum learning, multiple resolutions discriminators, multi-armed bandits, generative adversarial networks, smooth discriminators, multi-discriminator gan training, multiple experts.
2019-07-16
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
Thang Doan
Bogdan Mazoure
Audrey Durand
Joelle Pineau
R Devon Hjelm
Continuous control tasks in reinforcement learning are important because they provide an important framework for learning in high-dimensiona… (voir plus)l state spaces with deceptive rewards, where the agent can easily become trapped into suboptimal solutions. One way to avoid local optima is to use a population of agents to ensure coverage of the policy space, yet learning a population with the "best" coverage is still an open problem. In this work, we present a novel approach to population-based RL in continuous control that leverages properties of normalizing flows to perform attractive and repulsive operations between current members of the population and previously observed policies. Empirical results on the MuJoCo suite demonstrate a high performance gain for our algorithm compared to prior work, including Soft-Actor Critic (SAC).
2018-12-31
arXiv (prépublication)
doi.org
openreview.net
Contextual Bandits for Adapting Treatment in a Mouse Model of de Novo Carcinogenesis
Audrey Durand
Charis Achilleos
Demetris Iacovides
Katerina Strati
Georgios D. Mitsis
Joelle Pineau
2018-11-28
Proceedings of the 3rd Machine Learning for Healthcare Conference (publié)
proceedings.mlr.press
proceedings.mlr.press
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 … (voir plus)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 (publié)
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… (voir plus)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) (publié)
dblp.uni-trier.de