Publications

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
BigBrain 3D atlas of cortical layers: Cortical and laminar thickness gradients diverge in sensory and motor cortices
Konrad Wagstyl
Stéphanie Larocque
Guillem Cucurull
Claude Lepage
Joseph Paul Cohen
Sebastian Bludau
Nicola Palomero-Gallagher
Lindsay B. Lewis
Thomas Funck
Hannah Spitzer
Timo Dickscheid
Paul C. Fletcher
Adriana Romero
Karl Zilles
Katrin Amunts
Yoshua Bengio
Alan C. Evans
Histological atlases of the cerebral cortex, such as those made famous by Brodmann and von Economo, are invaluable for understanding human b… (see more)rain microstructure and its relationship with functional organization in the brain. However, these existing atlases are limited to small numbers of manually annotated samples from a single cerebral hemisphere, measured from 2D histological sections. We present the first whole-brain quantitative 3D laminar atlas of the human cerebral cortex. This atlas was derived from a 3D histological model of the human brain at 20 micron isotropic resolution (BigBrain), using a convolutional neural network to segment, automatically, the cortical layers in both hemispheres. Our approach overcomes many of the historical challenges with measurement of histological thickness in 2D and the resultant laminar atlas provides an unprecedented level of precision and detail. We utilized this BigBrain cortical atlas to test whether previously reported thickness gradients, as measured by MRI in sensory and motor processing cortices, were present in a histological atlas of cortical thickness, and which cortical layers were contributing to these gradients. Cortical thickness increased across sensory processing hierarchies, primarily driven by layers III, V and VI. In contrast, fronto-motor cortices showed the opposite pattern, with decreases in total and pyramidal layer thickness. These findings illustrate how this laminar atlas will provide a link between single-neuron morphology, mesoscale cortical layering, macroscopic cortical thickness and, ultimately, functional neuroanatomy.
2020-06-04
Public Library of Science (published)
doi.org
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
Coping With Simulators That Don't Always Return
Andrew Warrington
Saeid Naderiparizi
Frank N. Wood
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
proceedings.mlr.press
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui
Fan Zhou
Christian Gagné
Boyu Wang
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
proceedings.mlr.press
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
Philip Amortila
Doina Precup
Prakash Panangaden
Bellemare Marc-Emmanuel
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate it… (see more)s effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD(
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
doi.org
proceedings.mlr.press
Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning
Tianyu Li
Bogdan Mazoure
Doina Precup
Guillaume Rabusseau
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
doi.org
proceedings.mlr.press
Expressiveness and Learning of Hidden Quantum Markov Models
Sandesh M. Adhikary
Siddarth Srinivasan
Geoff Gordon
Byron Boots
Extending classical probabilistic reasoning using the quantum mechanical view of probability has been of recent interest, particularly in th… (see more)e development of hidden quantum Markov models (HQMMs) to model stochastic processes. However, there has been little progress in characterizing the expressiveness of such models and learning them from data. We tackle these problems by showing that HQMMs are a special subclass of the general class of observable operator models (OOMs) that do not suffer from the \emph{negative probability problem} by design. We also provide a feasible retraction-based learning algorithm for HQMMs using constrained gradient descent on the Stiefel manifold of model parameters. We demonstrate that this approach is faster and scales to larger models than previous learning algorithms.
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
proceedings.mlr.press
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
Si Yi Meng
Sharan Vaswani
Issam Hadj Laradji
Mark Schmidt
Simon Lacoste-Julien
We consider stochastic second-order methods for minimizing smooth and strongly-convex functions under an interpolation condition satisfied b… (see more)y over-parameterized models. Under this condition, we show that the regularized subsampled Newton method (R-SSN) achieves global linear convergence with an adaptive step-size and a constant batch-size. By growing the batch size for both the subsampled gradient and Hessian, we show that R-SSN can converge at a quadratic rate in a local neighbourhood of the solution. We also show that R-SSN attains local linear convergence for the family of self-concordant functions. Furthermore, we analyze stochastic BFGS algorithms in the interpolation setting and prove their global linear convergence. We empirically evaluate stochastic L-BFGS and a "Hessian-free" implementation of R-SSN for binary classification on synthetic, linearly-separable datasets and real datasets under a kernel mapping. Our experimental results demonstrate the fast convergence of these methods, both in terms of the number of iterations and wall-clock time.
2020-06-02
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
proceedings.mlr.press