Portrait of Audrey Durand

Audrey Durand

Associate Academic Member
Canada CIFAR AI Chair
Assistant Professor, Université Laval, Department of Computer Science and Software Engineering
Website
Google Scholar
X

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

Alexandre Larouche
PhD - Université Laval
alexandre.larouche@mila.quebec
Github
Google Scholar
Dorra Allegue
Postdoctorate - Université Laval
dorra-rakia.allegue@mila.quebec
Hadi Moazen
PhD - Université Laval
hadi.moazen@mila.quebec
Kaoutar Mimouni
Master's Research - Université Laval
kaoutar.mimouni@mila.quebec
Mathieu Godbout
PhD - Université Laval
mathieu.godbout@mila.quebec
Github
Maxime Heuillet
PhD - Université Laval
maxime.heuillet@mila.quebec
Randy Lefebvre
Master's Research - Université Laval
randy.lefebvre@mila.quebec
Yasmeen Hitti
PhD - McGill University
hittiyas@mila.quebec

Publications

Contextual Bandits for Adapting Treatment in a Mouse Model of de Novo Carcinogenesis
Audrey Durand
Charis Achilleos
Demetris C Iacovides
Katerina Strati
Georgios D. Mitsis
Joelle Pineau
In this work, we present a specific case study where we aim to design effective treatment allocation strategies and validate these using a m… (see more)ouse model of skin cancer. Collecting data for modelling treatments effectiveness on animal models is an expensive and time consuming process. Moreover, acquiring this information during the full range of disease stages is hard to achieve with a conventional random treatment allocation procedure, as poor treatments cause deterioration of subject health. We therefore aim to design an adaptive allocation strategy to improve the efficiency of data collection by allocating more samples for exploring promising treatments. We cast this application as a contextual bandit problem and introduce a simple and practical algorithm for exploration-exploitation in this framework. The work builds on a recent class of approaches for non-contextual bandits that relies on subsampling to compare treatment options using an equivalent amount of information. On the technical side, we extend the subsampling strategy to the case of bandits with context, by applying subsampling within Gaussian Process regression. On the experimental side, preliminary results using 10 mice with skin tumours suggest that the proposed approach extends by more than 50% the subjects life duration compared with baseline strategies: no treatment, random treatment allocation, and constant chemotherapeutic agent. By slowing the tumour growth rate, the adaptive procedure gathers information about treatment effectiveness on a broader range of tumour volumes, which is crucial for eventually deriving sequential pharmacological treatment strategies for cancer.
2018-11-29
Proceedings of the 3rd Machine Learning for Healthcare Conference (published)
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 … (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.
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.