Publications

Out-of-Distribution Generalization via Risk Extrapolation
David Krueger
Ethan Caballero
Joern-Henrik Jacobsen
Amy Zhang
Jonathan Binas
Dinghuai Zhang
Rémi Le Priol
Aaron Courville
Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To … (voir plus)tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model's sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anti-causal elements. We motivate this approach, Risk Extrapolation (REx), as a form of robust optimization over a perturbation set of extrapolated domains (MM-REx), and propose a penalty on the variance of training risks (V-REx) as a simpler variant. We prove that variants of REx can recover the causal mechanisms of the targets, while also providing some robustness to changes in the input distribution ("covariate shift"). By appropriately trading-off robustness to causally induced distributional shifts and covariate shift, REx is able to outperform alternative methods such as Invariant Risk Minimization in situations where these types of shift co-occur.
2021-06-30
Proceedings of the 38th International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting
Soumyasundar Pal
Liheng Ma
Yingxue Zhang
Mark J. Coates
Spatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical mod… (voir plus)els often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the art point forecasting methods.
2021-06-30
Proceedings of the 38th International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Smart About Meds (SAM): a pilot randomized controlled trial of a mobile application to improve medication adherence following hospital discharge
Bettina Habib
David Buckeridge
Melissa Bustillo
Santiago Nicolas Marquez
Manish Thakur
Thai Tran
Daniala L. Weir
Robyn Tamblyn
The objectives of this pilot study were (1) to assess the feasibility of a larger evaluation of Smart About Meds (SAM), a patient-centered m… (voir plus)edication management mobile application, and (2) to evaluate SAM’s potential to improve outcomes of interest, including adherence to medication changes made at hospital discharge and the occurrence of adverse events. We conducted a pilot randomized controlled trial among patients discharged from internal medicine units of an academic health center between June 2019 and March 2020. Block randomization was used to randomize patients to intervention (received access to SAM at discharge) or control (received usual care). Patients were followed for 30 days post-discharge, during which app use was recorded. Pharmacy claims data were used to measure adherence to medication changes made at discharge, and physician billing data were used to identify emergency department visits and hospital readmissions during follow-up. Forty-nine patients were eligible for inclusion in the study at hospital discharge (23 intervention, 26 control). In the 30 days of post-discharge, 15 (65.2%) intervention patients used the SAM app. During this period, intervention patients adhered to a larger proportion of medication changes (83.7%) than control patients (77.8%), including newly prescribed medications (72.7% vs 61.7%) and dose changes (90.9% vs 81.8%). A smaller proportion of intervention patients (8.7%) were readmitted to hospital during follow-up than control patients (15.4%). The high uptake of SAM among intervention patients supports the feasibility of a larger trial. Results also suggest that SAM has the potential to enhance adherence to medication changes and reduce the risk of downstream adverse events. This hypothesis needs to be tested in a larger trial. Clinicaltrials.gov, registration number NCT04676165.
2021-06-30
JAMIA Open (publié)
doi.org
Measures of balance in combinatorial optimization
Philippe Olivier
Andrea Lodi
Gilles Pesant
2021-06-24
4OR (publié)
doi.org
Deep learning for AI
Yoshua Bengio
Yann Lecun
Geoffrey Hinton
How can neural networks learn the rich internal representations required for difficult tasks such as recognizing objects or understanding la… (voir plus)nguage?
2021-06-20
Communications of the ACM (publié)
doi.org
Large-Scale Intrinsic Functional Brain Organization Emerges from Three Canonical Spatiotemporal Patterns
Taylor Bolt
Jason S. Nomi
Danilo Bzdok
Catie Chang
B.T. Yeo
Lucina Q. Uddin
Shella Keilholz
2021-06-19
(publié)
doi.org
Digitizing a sustainable future
Lucia A. Reisch
Lucas Joppa
Peter Howson
Artur Gil
Panayiota Alevizou
Nina Michaelidou
Ruby Appiah-Campbell
Tilman Santarius
Susanne Köhler
Massimo Pizzol
Pia-Johanna Schweizer
Dipti Srinivasan
Lynn H. Kaack
Priya L. Donti
David Rolnick
2021-06-17
One Earth (publié)
doi.org
The Cost of Untracked Diversity in Brain-Imaging Prediction
Oualid Benkarim
Casey Paquola
Bo-yong Park
Valeria Kebets
Seok-Jun Hong
Reinder Vos de Wael
Shaoshi Zhang
B.T. Thomas Yeo
Michael Eickenberg
Tian Ge
Jean-Baptiste Poline
Boris Bernhardt
Danilo Bzdok
Brain-imaging research enjoys increasing adoption of supervised machine learning for singlesubject disease classification. Yet, the success … (voir plus)of these algorithms likely depends on population diversity, including demographic differences and other factors that may be outside of primary scientific interest. Here, we capitalize on propensity scores as a composite confound index to quantify diversity due to major sources of population stratification. We delineate the impact of population heterogeneity on the predictive accuracy and pattern stability in two separate clinical cohorts: the Autism Brain Imaging Data Exchange (ABIDE, n=297) and the Healthy Brain Network (HBN, n=551). Across various analysis scenarios, our results uncover the extent to which cross-validated prediction performances are interlocked with diversity. The instability of extracted brain patterns attributable to diversity is located preferentially to the default mode network. Our collective findings highlight the limitations of prevailing deconfounding practices in mitigating the full consequences of population diversity.
2021-06-16
bioRxiv (prépublication)
doi.org
Improving Continuous Normalizing Flows using a Multi-Resolution Framework
Vikram Voleti
Chris Finlay
Adam Oberman
Christopher Pal
Recent work has shown that Continuous Normalizing Flows (CNFs) can serve as generative models of images with exact likelihood calculation an… (voir plus)d invertible generation/density estimation. In this work we introduce a Multi-Resolution variant of such models (MRCNF). We introduce a transformation between resolutions that allows for no change in the log likelihood. We show that this approach yields comparable likelihood values for various image datasets, with improved performance at higher resolutions, with fewer parameters, using only 1 GPU.
2021-06-14
ICML.cc/2021/Workshop/INNF (poster)
openreview.net
openreview.net
Randomized Exploration for Reinforcement Learning with General Value Function Approximation
Haque Ishfaq
Qiwen Cui
Viet Nguyen
Alex Ayoub
Zhuoran Yang
Zhaoran Wang
Doina Precup
Lin F. Yang
2021-06-14
ArXiv (prépublication)
proceedings.mlr.press
proceedings.mlr.press
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Yashas Annadani
Jonas Rothfuss
Alexandre Lacoste
Nino Scherrer
Anirudh Goyal
Yoshua Bengio
Stefan Bauer
Learning the causal structure that underlies data is a crucial step towards robust real-world decision making. The majority of existing work… (voir plus) in causal inference focuses on determining a single directed acyclic graph (DAG) or a Markov equivalence class thereof. However, a crucial aspect to acting intelligently upon the knowledge about causal structure which has been inferred from finite data demands reasoning about its uncertainty. For instance, planning interventions to find out more about the causal mechanisms that govern our data requires quantifying epistemic uncertainty over DAGs. While Bayesian causal inference allows to do so, the posterior over DAGs becomes intractable even for a small number of variables. Aiming to overcome this issue, we propose a form of variational inference over the graphs of Structural Causal Models (SCMs). To this end, we introduce a parametric variational family modelled by an autoregressive distribution over the space of discrete DAGs. Its number of parameters does not grow exponentially with the number of variables and can be tractably learned by maximising an Evidence Lower Bound (ELBO). In our experiments, we demonstrate that the proposed variational posterior is able to provide a good approximation of the true posterior.
2021-06-13
ArXiv (prépublication)
arxiv.org
arxiv.org
Comparative Study of Learning Outcomes for Online Learning Platforms
Francois St-Hilaire
Nathan J. Burns
Robert Belfer
Muhammad Shayan
Ariella Smofsky
Dung D. Vu
Antoine Frau
Joseph Potochny
Farid Faraji
Vincent Pavero
Neroli Ko
Ansona Onyi Ching
Sabina Elkins
A. Stepanyan
Adela Matajova
Laurent Charlin
Yoshua Bengio
Iulian V. Serban
Ekaterina Kochmar
2021-06-11
Lecture Notes in Computer Science (publié)
doi.org
arxiv.org