Publications

Untangling tradeoffs between recurrence and self-attention in neural networks
Giancarlo Kerg
Bhargav Kanuparthi
Anirudh Goyal
Kyle Goyette
Yoshua Bengio
Guillaume Lajoie
2020-06-15
ArXiv (preprint)
arxiv.org
arxiv.org
User-Centered Design for Promoting Patient Engagement in Chronic Diseases Management: The Development of CONCERTO+
Marie-Pierre Gagnon
Mame Ndiaye
Alain Larouche
Guylaine Chabot
Christian Chabot
Ronald Buyl
Jean-Paul Fortin
Anik Giguère
Annie LeBlanc
France Légaré
Aude Motulsky
Claude Sicotte
Holly O Witteman
Eric Kavanagh
Frédéric Lépinay
Jacynthe Roberge
Hina Hakim
Myriam Brunet-Gauthier
Carole Délétroz
S. A. Rahimi … (see 2 more)
Jack Tchuente
Maxime Sasseville
Multimorbidity increases care needs among people with chronic diseases. In order to support communication between patients, their informal c… (see more)aregivers and their healthcare teams, we developed CONCERTO+, a patient portal for chronic disease management in primary care. A user-centered design comprising 3 iterations with patients and informal caregivers was performed. Clinicians were also invited to provide feedback on the feasibility of the solution. Several improvements were brought to CONCERTO+, and it is now ready to be implemented in real-life setting.
2020-06-15
Medical Informatics Europe (published)
doi.org
Learning Causal Models Online
Khurram Javed
Martha White
Yoshua Bengio
2020-06-11
ArXiv (preprint)
arxiv.org
arxiv.org
To Each Optimizer a Norm, To Each Norm its Generalization
Sharan Vaswani
Reza Babanezhad Harikandeh
Jose Gallego
Aaron Mishkin
Simon Lacoste-Julien
Nicolas Roux
We study the implicit regularization of optimization methods for linear models interpolating the training data in the under-parametrized and… (see more) over-parametrized regimes. Since it is difficult to determine whether an optimizer converges to solutions that minimize a known norm, we flip the problem and investigate what is the corresponding norm minimized by an interpolating solution. Using this reasoning, we prove that for over-parameterized linear regression, projections onto linear spans can be used to move between different interpolating solutions. For under-parameterized linear classification, we prove that for any linear classifier separating the data, there exists a family of quadratic norms ||.||_P such that the classifier's direction is the same as that of the maximum P-margin solution. For linear classification, we argue that analyzing convergence to the standard maximum l2-margin is arbitrary and show that minimizing the norm induced by the data results in better generalization. Furthermore, for over-parameterized linear classification, projections onto the data-span enable us to use techniques from the under-parameterized setting. On the empirical side, we propose techniques to bias optimizers towards better generalizing solutions, improving their test performance. We validate our theoretical results via synthetic experiments, and use the neural tangent kernel to handle non-linear models.
2020-06-10
ArXiv (preprint)
arxiv.org
arxiv.org
Glossary for public health surveillance in the age of data science
Arnaud Chiolero
David L Buckeridge
Public health surveillance is the ongoing systematic collection, analysis and interpretation of data, closely integrated with the timely dis… (see more)semination of the resulting information to those responsible for preventing and controlling disease and injury. With the rapid development of data science, encompassing big data and artificial intelligence, and with the exponential growth of accessible and highly heterogeneous health-related data, from healthcare providers to user-generated online content, the field of surveillance and health monitoring is changing rapidly. It is, therefore, the right time for a short glossary of key terms in public health surveillance, with an emphasis on new data-science developments in the field.
2020-06-09
Journal of Epidemiology and Community Health (published)
doi.org
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM
Iulian V. Serban
Varun Gupta
Ekaterina Kochmar
Dung D. Vu
Robert Belfer
Joelle Pineau
Aaron Courville
Laurent Charlin
Yoshua Bengio
2020-06-09
Artificial Intelligence in Education (published)
doi.org
arxiv.org
Multi-agent Assortment Optimization in Sequential Matching Markets
Alfredo Torrico
Margarida Carvalho
Andrea Lodi
2020-06-07
ArXiv (preprint)
arxiv.org
arxiv.org
Provable Guarantees for General Two-sided Sequential Matching Markets
Alfredo Torrico
Margarida Carvalho
Andrea Lodi
Two-sided markets have become increasingly more important during the last years, mostly because of their numerous applications in housing, l… (see more)abor and dating. Consumer-supplier matching platforms pose several technical challenges, specially due to the trade-off between recommending suitable suppliers to consumers and avoiding collisions among consumers' preferences. In this work, we study a general version of the two-sided sequential matching model introduced by Ashlagi et al. (2019). The setting is the following: we (the platform) offer a menu of suppliers to each consumer. Then, every consumer selects, simultaneously and independently, to match with a supplier or to remain unmatched. Suppliers observe the subset of consumers that selected them, and choose either to match a consumer or leave the system. Finally, a match takes place if both the consumer and the supplier sequentially select each other. Each agent's behavior is probabilistic and determined by a regular discrete choice model. Our objective is to choose an assortment family that maximizes the expected cardinality of the matching. Given the computational complexity of the problem, we show several provable guarantees for the general model, which in particular, significantly improve the approximation factors previously obtained.
2020-06-07
arXiv.org (preprint)
dblp.uni-trier.de
Dark control: The default mode network as a reinforcement learning agent
Elvis Dohmatob
Guillaume Dumas
Danilo Bzdok
The default mode network (DMN) is believed to subserve the baseline mental activity in humans. Its higher energy consumption compared to oth… (see more)er brain networks and its intimate coupling with conscious awareness are both pointing to an unknown overarching function. Many research streams speak in favor of an evolutionarily adaptive role in envisioning experience to anticipate the future. In the present work, we propose a process model that tries to explain how the DMN may implement continuous evaluation and prediction of the environment to guide behavior. The main purpose of DMN activity, we argue, may be described by Markov decision processes that optimize action policies via value estimates through vicarious trial and error. Our formal perspective on DMN function naturally accommodates as special cases previous interpretations based on (a) predictive coding, (b) semantic associations, and (c) a sentinel role. Moreover, this process model for the neural optimization of complex behavior in the DMN offers parsimonious explanations for recent experimental findings in animals and humans.
2020-06-04
Human Brain Mapping (unknown)
doi.org
Prioritization of patients access to outpatient augmentative and alternative communication services in Quebec: a decision tool
S. A. Rahimi
Julien Dery
Marie-Eve Lamontagne
Afshin Jamshidi
Emilie Lacroix
Angel Ruiz
Daoud Ait-Kadi
François Routhier
2020-06-04
Disability and Rehabilitation: Assistive Technology (published)
doi.org
Precision public health: Dream or reality?
Maureen Dobbins
David L Buckeridge
2020-06-03
Canada communicable disease report = Releve des maladies transmissibles au Canada (published)
doi.org
Accelerating Smooth Games by Manipulating Spectral Shapes
Waïss Azizian
Damien Scieur
Ioannis Mitliagkas
Simon Lacoste-Julien
Gauthier Gidel
We use matrix iteration theory to characterize acceleration in smooth games. We define the spectral shape of a family of games as the set co… (see more)ntaining all eigenvalues of the Jacobians of standard gradient dynamics in the family. Shapes restricted to the real line represent well-understood classes of problems, like minimization. Shapes spanning the complex plane capture the added numerical challenges in solving smooth games. In this framework, we describe gradient-based methods, such as extragradient, as transformations on the spectral shape. Using this perspective, we propose an optimal algorithm for bilinear games. For smooth and strongly monotone operators, we identify a continuum between convex minimization, where acceleration is possible using Polyak's momentum, and the worst case where gradient descent is optimal. Finally, going beyond first-order methods, we propose an accelerated version of consensus optimization.
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
doi.org
proceedings.mlr.press