Portrait de Tegan Maharaj

Tegan Maharaj

Membre académique principal
tegan.maharaj@mila.quebec
Professeure adjointe en apprentissage automatique, HEC Montréal, Département de sciences de la décision
Sujets de recherche
Apprentissage de représentations
Apprentissage multimodal
Apprentissage profond
Systèmes dynamiques
Théorie de l'apprentissage automatique
Site web
Google Scholar

Biographie

Je suis professeure adjointe au Département de sciences de la décision à HEC Montréal. Mes objectifs de recherche sont de contribuer à la compréhension et aux techniques de la science du développement responsable de l’IA, tout en appliquant utilement l’IA à des problèmes écologiques à fort impact liés au changement climatique, à l’épidémiologie, à l’alignement de l’IA et à l’évaluation des impacts écologiques. Mes travaux récents portent sur deux thèmes : l’utilisation de modèles profonds pour l’analyse des politiques et l’atténuation des risques; et la conception de données ou d’environnements de tests unitaires pour évaluer empiriquement le comportement d’apprentissage ou simuler le déploiement d’un système d’IA. N’hésitez pas à me contacter pour toute collaboration dans ces domaines.

Je suis généralement intéressée par l’étude de ce qui « entre » dans les modèles profonds : non seulement les données, mais l’environnement d’apprentissage plus globalement, qui comprend la conception/spécification des tâches, la fonction de perte et la régularisation, ainsi que le contexte sociétal du déploiement, notamment les considérations de confidentialité, les tendances et les incitatifs, les normes et les préjugés humains. Je suis préoccupée et passionnée par l’éthique de l’IA, la sécurité et l’application de l’apprentissage machine à la gestion de l’environnement, à la santé et au bien-être social.

Étudiants actuels

Carol Altimas
Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e :
Étienne Laliberté

Publications

Predicting Infectiousness for Proactive Contact Tracing
Yoshua Bengio
Prateek Gupta
Tegan Maharaj
Nasim Rahaman
Martin Weiss
Tristan Deleu
Eilif Benjamin Muller
Meng Qu
Victor Schmidt
Pierre-Luc St-Charles
Hannah Alsdurf
Olexa Bilaniuk
David Buckeridge
gaetan caron
pierre luc carrier
Joumana Ghosn
satya ortiz gagne
Chris Pal
Irina Rish
Bernhard Schölkopf … (voir 3 de plus)
Abhinav Sharma
Jian Tang
andrew williams
The COVID-19 pandemic has spread rapidly worldwide, overwhelming manual contact tracing in many countries and resulting in widespread lockdo… (voir plus)wns for emergency containment. Large-scale digital contact tracing (DCT) has emerged as a potential solution to resume economic and social activity while minimizing spread of the virus. Various DCT methods have been proposed, each making trade-offs between privacy, mobility restrictions, and public health. The most common approach, binary contact tracing (BCT), models infection as a binary event, informed only by an individual's test results, with corresponding binary recommendations that either all or none of the individual's contacts quarantine. BCT ignores the inherent uncertainty in contacts and the infection process, which could be used to tailor messaging to high-risk individuals, and prompt proactive testing or earlier warnings. It also does not make use of observations such as symptoms or pre-existing medical conditions, which could be used to make more accurate infectiousness predictions. In this paper, we use a recently-proposed COVID-19 epidemiological simulator to develop and test methods that can be deployed to a smartphone to locally and proactively predict an individual's infectiousness (risk of infecting others) based on their contact history and other information, while respecting strong privacy constraints. Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT). We find a deep-learning based PCT method which improves over BCT for equivalent average mobility, suggesting PCT could help in safe re-opening and second-wave prevention.
2021-01-12
ICLR.cc/2021/Conference (spotlight)
openreview.net
openreview.net
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
Prateek Gupta
Tegan Maharaj
Martin Weiss
Nasim Rahaman
Hannah Alsdurf
Abhinav Sharma
Nanor Minoyan
Soren Harnois-Leblanc
Victor Schmidt
Pierre-Luc St-Charles
Tristan Deleu
andrew williams
Akshay Patel
Meng Qu
Olexa Bilaniuk
gaetan caron
pierre luc carrier
satya ortiz gagne
Marc-Andre Rousseau
David Buckeridge … (voir 9 de plus)
Joumana Ghosn
Yang Zhang
Bernhard Schölkopf
Jian Tang
Irina Rish
Chris Pal
Joanna Merckx
Eilif Benjamin Muller
Yoshua Bengio
2020-10-02
OpenReview.net/Anonymous_Preprint (inconnu)
openreview.net
openreview.net
COVI White Paper
Hannah Alsdurf
Yoshua Bengio
Tristan Deleu
Prateek Gupta
Daphne Ippolito
Richard Janda
Max Jarvie
Tyler J. Kolody
Sekoul Krastev
Tegan Maharaj
Robert Obryk
Dan Pilat
Valerie Pisano
Benjamin Prud'homme
Meng Qu
Nasim Rahaman
Irina Rish
Jean-franois Rousseau
Abhinav Sharma
Brooke Struck … (voir 3 de plus)
Jian Tang
Martin Weiss
Yun William Yu
2020-05-18
ArXiv (prépublication)
arxiv.org
arxiv.org
COVI White Paper
Hannah Alsdurf
Yoshua Bengio
Tristan Deleu
Prateek Gupta
Daphne Ippolito
Richard Janda
Max Jarvie
Tyler J. Kolody
Sekoul Krastev
Tegan Maharaj
Robert Obryk
Dan Pilat
Valerie Pisano
Benjamin Prud'homme
Meng Qu
Nasim Rahaman
Irina Rish
Jean-franois Rousseau
Abhinav Sharma
Brooke Struck … (voir 3 de plus)
Jian Tang
Martin Weiss
Yun William Yu
2020-05-18
ArXiv (prépublication)
arxiv.org
arxiv.org
COVI White Paper
Hannah Alsdurf
Yoshua Bengio
Tristan Deleu
Prateek Gupta
Daphne Ippolito
Richard Janda
Max Jarvie
Tyler J. Kolody
Sekoul Krastev
Tegan Maharaj
Robert Obryk
Dan Pilat
Valerie Pisano
Benjamin Prud'homme
Meng Qu
Nasim Rahaman
Irina Rish
Jean-franois Rousseau
Abhinav Sharma
Brooke Struck … (voir 3 de plus)
Jian Tang
Martin Weiss
Yun William Yu
The SARS-CoV-2 (Covid-19) pandemic has caused significant strain on public health institutions around the world. Contact tracing is an essen… (voir plus)tial tool to change the course of the Covid-19 pandemic. Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections. Personalized peer-to-peer contact tracing through the use of mobile apps has the potential to shift the paradigm. Some countries have deployed centralized tracking systems, but more privacy-protecting decentralized systems offer much of the same benefit without concentrating data in the hands of a state authority or for-profit corporations. Machine learning methods can circumvent some of the limitations of standard digital tracing by incorporating many clues and their uncertainty into a more graded and precise estimation of infection risk. The estimated risk can provide early risk awareness, personalized recommendations and relevant information to the user. Finally, non-identifying risk data can inform epidemiological models trained jointly with the machine learning predictor. These models can provide statistical evidence for the importance of factors involved in disease transmission. They can also be used to monitor, evaluate and optimize health policy and (de)confinement scenarios according to medical and economic productivity indicators. However, such a strategy based on mobile apps and machine learning should proactively mitigate potential ethical and privacy risks, which could have substantial impacts on society (not only impacts on health but also impacts such as stigmatization and abuse of personal data). Here, we present an overview of the rationale, design, ethical considerations and privacy strategy of `COVI,' a Covid-19 public peer-to-peer contact tracing and risk awareness mobile application developed in Canada.
2020-05-18
ArXiv (prépublication)
arxiv.org
arxiv.org
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
Miles Brundage
Shahar Avin
Jasmine Wang
Haydn Belfield
Gretchen Krueger
Gillian K. Hadfield
Heidy Khlaaf
Jingying Yang
H. Toner
Ruth Catherine Fong
Tegan Maharaj
Pang Wei Koh
Sara Hooker
Jade Leung
Andrew John Trask
Emma Bluemke
Jonathan Lebensbold
Cullen C. O'keefe
Mark Koren
Th'eo Ryffel … (voir 39 de plus)
JB Rubinovitz
Tamay Besiroglu
Federica Carugati
Jack Clark
Peter Eckersley
Sarah de Haas
Maritza L. Johnson
Ben Laurie
Alex Ingerman
Igor Krawczuk
Amanda Askell
Rosario Cammarota
A. Lohn
David Scott Krueger
Charlotte Stix
Peter Mark Henderson
Logan Graham
Carina E. A. Prunkl
Bianca Martin
Elizabeth Seger
Noa Zilberman
Sean O hEigeartaigh
Frens Kroeger
Girish Sastry
R. Kagan
Adrian Weller
Brian Shek-kam Tse
Elizabeth Barnes
Allan Dafoe
Paul D. Scharre
Ariel Herbert-Voss
Martijn Rasser
Shagun Sodhani
Carrick Flynn
Thomas Krendl Gilbert
Lisa Dyer
Saif M. Khan
Yoshua Bengio
Markus Anderljung
2020-04-15
ArXiv (prépublication)
arxiv.org
arxiv.org
COVI White Paper-Version 1.1
Hannah Alsdurf
Yoshua Bengio
Tristan Deleu
Prateek Gupta
Daphne Ippolito
Richard Janda
Max Jarvie
Tyler J. Kolody
Sekoul Krastev
Tegan Maharaj
Robert Obryk
Dan Pilat
Valerie Pisano
Benjamin Prud'homme
Meng Qu
Nasim Rahaman
Irina Rish
Jean-franois Rousseau
Abhinav Sharma
Brooke Struck … (voir 3 de plus)
Jian Tang
Martin Weiss
Yun William Yu
The SARS-CoV-2 (Covid-19) pandemic has resulted in significant strain on health care and public health institutions around the world. Contac… (voir plus)t tracing is an essential tool for public health officials and local communities to change the course of the Covid-19 pandemic. Standard manual contact tracing of people infected with Covid-19, while the current gold standard, has significant challenges that limit the ability of public health authorities to minimize community infections. Personalized peer-to-peer contact tracing through the use of mobile applications has the potential to shift the paradigm of Covid-19 community spread. Although some countries have deployed centralized tracking systems through either GPS or Bluetooth, more privacy-protecting decentralized systems offer much of the same benefit without concentrating data in the hands of a state authority or in for-profit corporations. Additionally, machine learning methods can be used to circumvent some of the limitations of standard digital tracing by incorporating many clues (including medical conditions, self-reported symptoms, and numerous encounters with people at different risk levels, for different durations and distances) and their uncertainty into a more graded and precise estimation of infection and contagion risk. The estimated risk can be used to provide early risk awareness, personalized recommendations and relevant information to the user and connect them to health services. Finally, the non-identifying data about these risks can inform detailed epidemiological models trained jointly with the machine learning predictor, and these models can provide statistical evidence for the interaction and importance of different factors involved in the transmission of the disease. They can also be used to monitor, evaluate and optimize different health policy and confinement/deconfinement scenarios according to medical and economic productivity indicators. However, such a strategy based on mobile apps and machine learning should proactively mitigate potential ethical and privacy risks, which could have substantial impacts on society (not only impacts on health but also impacts such as stigmatization and abuse of personal data). Here, we present an overview of the rationale, design, ethical considerations and privacy strategy of ‘COVI,’ a Covid-19 public peer-to-peer contact tracing and risk awareness mobile application developed in Canada. Addendum 2020-07-14: The government of Canada has declined to endorse COVI and will be promoting a different app for decentralized contact tracing. In the interest of preventing fragmentation of the app landscape, COVI will therefore not be deployed to end users. We are currently still in the process of finalizing the project, and plan to release our code and models for academic consumption and to make them accessible to other States should they wish to deploy an app based on or inspired by said code and models. University of Ottawa, Mila, Université de Montréal, The Alan Turing Institute, University of Oxford, University of Pennsylvania, McGill University, Borden Ladner Gervais LLP, The Decision Lab, HEC Montréal, Max Planck Institute, Libéo, University of Toronto. Corresponding author general: richard.janda@mcgill.ca Corresponding author for public health: abhinav.sharma@mcgill.ca Corresponding author for privacy: ywyu@math.toronto.edu Corresponding author for machine learning: yoshua.bengio@mila.quebec Corresponding author for user perspective: brooke@thedecisionlab.com Corresponding author for technical implementation: jean-francois.rousseau@libeo.com 1 ar X iv :2 00 5. 08 50 2v 2 [ cs .C R ] 2 7 Ju l 2 02 0
Deep Learning recognizes weather and climate patterns
Karthik Kashinath
M. Prabhat
Mayur Mudigonda
Ankur Mahesh
Sookyung Kim
Yunjie Liu
Samira Ebrahimi Kahou
B. Toms
Evan Racah
Christopher Beckham
Chris Pal
Tegan Maharaj
Jim Biard
K. Kunkel
Dean Nesbit Williams
Travis O'Brien
M. Wehner
W. Collins
A Dataset and Exploration of Models for Understanding Video Data through Fill-in-the-Blank Question-Answering
Tegan Maharaj
Nicolas Ballas
Anna Rohrbach
Aaron Courville
Chris Pal
While deep convolutional neural networks frequently approach or exceed human-level performance in benchmark tasks involving static images, e… (voir plus)xtending this success to moving images is not straightforward. Video understanding is of interest for many applications, including content recommendation, prediction, summarization, event/object detection, and understanding human visual perception. However, many domains lack sufficient data to explore and perfect video models. In order to address the need for a simple, quantitative benchmark for developing and understanding video, we present MovieFIB, a fill-in-the-blank question-answering dataset with over 300,000 examples, based on descriptive video annotations for the visually impaired. In addition to presenting statistics and a description of the dataset, we perform a detailed analysis of 5 different models predictions, and compare these with human performance. We investigate the relative importance of language, static (2D) visual features, and moving (3D) visual features, the effects of increasing dataset size, the number of frames sampled, and of vocabulary size. We illustrate that: this task is not solvable by a language model alone, our model combining 2D and 3D visual information indeed provides the best result, all models perform significantly worse than human-level. We provide human evaluation for responses given by different models and find that accuracy on the MovieFIB evaluation corresponds well with human judgment. We suggest avenues for improving video models, and hope that the MovieFIB challenge can be useful for measuring and encouraging progress in this very interesting field.
2017-07-21
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (publié)
doi.org
arxiv.org
A Closer Look at Memorization in Deep Networks
Devansh Arpit
Stanisław Jastrzębski
Nicolas Ballas
David Scott Krueger
Emmanuel Bengio
Maxinder S. Kanwal
Tegan Maharaj
Asja Fischer
Aaron Courville
Yoshua Bengio
Simon Lacoste-Julien
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While dee… (voir plus)p networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differences in gradient-based optimization of deep neural networks (DNNs) on noise vs. real data. We also demonstrate that for appropriately tuned explicit regularization (e.g., dropout) we can degrade DNN training performance on noise datasets without compromising generalization on real data. Our analysis suggests that the notions of effective capacity which are dataset independent are unlikely to explain the generalization performance of deep networks when trained with gradient based methods because training data itself plays an important role in determining the degree of memorization.
2017-07-17
Proceedings of the 34th International Conference on Machine Learning (publié)
proceedings.mlr.press
arxiv.org
Deep Nets Don't Learn via Memorization
David Scott Krueger
Nicolas Ballas
Stanisław Jastrzębski
Devansh Arpit
Maxinder S. Kanwal
Tegan Maharaj
Emmanuel Bengio
Asja Fischer
Aaron Courville
We use empirical methods to argue that deep neural networks (DNNs) do not achieve their performance by memorizing training data in spite of … (voir plus)overlyexpressive model architectures. Instead, they learn a simple available hypothesis that fits the finite data samples. In support of this view, we establish that there are qualitative differences when learning noise vs. natural datasets, showing: (1) more capacity is needed to fit noise, (2) time to convergence is longer for random labels, but shorter for random inputs, and (3) that DNNs trained on real data examples learn simpler functions than when trained with noise data, as measured by the sharpness of the loss function at convergence. Finally, we demonstrate that for appropriately tuned explicit regularization, e.g. dropout, we can degrade DNN training performance on noise datasets without compromising generalization on real data.
2017-02-17
International Conference on Learning Representations (publié)
dblp.uni-trier.de