David Rolnick

Biographie

David Rolnick est professeur adjoint et titulaire d’une chaire en IA Canada-CIFAR à l'École d'informatique de l'Université McGill et membre académique principal de Mila – Institut québécois d’intelligence artificielle. Ses travaux portent sur les applications de l'apprentissage automatique dans la lutte contre le changement climatique. Il est cofondateur et président de Climate Change AI et codirecteur scientifique de Sustainability in the Digital Age. David Rolnick a obtenu un doctorat en mathématiques appliquées du Massachusetts Institute of Technology (MIT). Il a été chercheur postdoctoral en sciences mathématiques à la National Science Foundation (NSF), chercheur diplômé à la NSF et boursier Fulbright. Il a figuré sur la liste des « 35 innovateurs de moins de 35 ans » de la MIT Technology Review en 2021.

Étudiants actuels

Benjamin Akera Binen

Collaborateur·rice alumni - McGill

Collaborateur·rice alumni - UdeM

Mohit Anand

Collaborateur·rice de recherche - The University of Dresden, Helmholtz Centre for Environmental Research Leipzig

Ayush Ayush Prasad

Collaborateur·rice de recherche

Viktoriia Baibakova

Collaborateur·rice de recherche

Nikolaos Ioannis Bountos

Collaborateur·rice de recherche - National Observatory of Athens

Collaborateur·rice de recherche

Michael Bunsen

Collaborateur·rice de recherche - McGill

Juan Sebastián Cañas

Collaborateur·rice de recherche

Collaborateur·rice de recherche - N/A

Co-superviseur⋅e :

Yoshua Bengio

Yuyan Chen

Maîtrise recherche - McGill

Eya Cherif

Stagiaire de recherche - Leipzig University

Alexandre Duval

Collaborateur·rice de recherche - Université Paris-Saclay

Amna El-Mustafa

Collaborateur·rice de recherche

Paula Harder

Collaborateur·rice de recherche

Alex Hernandez-Garcia

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche - UdeM

Christina Humer

Collaborateur·rice de recherche - Johannes Kepler University

Gaurav Iyer

Maîtrise recherche - McGill

Doctorat - McGill

Devin Kwok

Doctorat - McGill

Vanessa Mac

Collaborateur·rice de recherche - University of Waterloo

David Alexandre Mickisch

Collaborateur·rice de recherche

Felix Andreas Nahrstedt

Stagiaire de recherche - UdeM

Arthur Ouaknine

Postdoctorat - McGill

Co-superviseur⋅e :

Lena Podina

Doctorat - University of Waterloo

Co-superviseur⋅e :

Doctorat - UdeM

Collaborateur·rice de recherche

Marlena Reil

Maîtrise recherche - McGill

Pratinav Seth

Collaborateur·rice de recherche

seth.pratinav@gmail.com

Collaborateur·rice de recherche - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)

Co-superviseur⋅e :

Yoshua Bengio

Ilija Trajković

Collaborateur·rice de recherche - Karlsruhe Institute of Technology

Doctorat - McGill

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice de recherche

anna.viklund@mila.quebec

Doctorat - McGill

Collaborateur·rice alumni - McGill

Qidong Yang

Collaborateur·rice de recherche

qidong.yang@mila.quebec

Publications

Multi-variable Hard Physical Constraints for Climate Model Downscaling

Jose Gonz'alez-Abad

'Alex Hern'andez-Garc'ia

Paula Harder

Jos'e Manuel Guti'errez

2023-08-02

ArXiv (prépublication)

FAENet: Frame Averaging Equivariant GNN for Materials Modeling

Alexandre AGM Duval

Victor Schmidt

Alex Hernandez-Garcia

Santiago Miret

Fragkiskos D. Malliaros

Yoshua Bengio

Applications of machine learning techniques for materials modeling typically involve functions known to be equivariant or invariant to speci… (voir plus)fic symmetries. While graph neural networks (GNNs) have proven successful in such tasks, they enforce symmetries via the model architecture, which often reduces their expressivity, scalability and comprehensibility. In this paper, we introduce (1) a flexible framework relying on stochastic frame-averaging (SFA) to make any model E(3)-equivariant or invariant through data transformations. (2) FAENet: a simple, fast and expressive GNN, optimized for SFA, that processes geometric information without any symmetrypreserving design constraints. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling on the OC20 dataset (S2EF, IS2RE) as well as common molecular modeling tasks (QM9, QM7-X). A package implementation is available at https://faenet.readthedocs.io.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

Hidden Symmetries of ReLU Networks

J. Grigsby

Elisenda Grigsby

Kathryn Lindsey

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

Maximal Initial Learning Rates in Deep ReLU Networks

Gaurav Iyer

Boris Hanin

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

Fourier Neural Operators for Arbitrary Resolution Climate Data Downscaling

Qidong Yang

Alex Hernandez-Garcia

Paula Harder

Venkatesh Ramesh

Prasanna Sattegeri

D. Szwarcman

C. Watson

Climate simulations are essential in guiding our understanding of climate change and responding to its effects. However, it is computational… (voir plus)ly expensive to resolve complex climate processes at high spatial resolution. As one way to speed up climate simulations, neural networks have been used to downscale climate variables from fast-running low-resolution simulations, but high-resolution training data are often unobtainable or scarce, greatly limiting accuracy. In this work, we propose a downscaling method based on the Fourier neural operator. It trains with data of a small upsampling factor and then can zero-shot downscale its input to arbitrary unseen high resolution. Evaluated both on ERA5 climate model data and on the Navier-Stokes equation solution data, our downscaling model significantly outperforms state-of-the-art convolutional and generative adversarial downscaling models, both in standard single-resolution downscaling and in zero-shot generalization to higher upsampling factors. Furthermore, we show that our method also outperforms state-of-the-art data-driven partial differential equation solvers on Navier-Stokes equations. Overall, our work bridges the gap between simulation of a physical process and interpolation of low-resolution output, showing that it is possible to combine both approaches and significantly improve upon each other.

2023-05-23

ArXiv (prépublication)

Bird Distribution Modelling using Remote Sensing and Citizen Science data

Mélisande Teng

Amna Elmustafa

Benjamin Akera

Hugo Larochelle

2023-05-01

ArXiv (prépublication)

Lightweight, Pre-trained Transformers for Remote Sensing Timeseries

Gabriel Tseng

Ruben Cartuyvels

Ivan Zvonkov

Mirali Purohit

Hannah Kerner

Machine learning methods for satellite data have a range of societally relevant applications, but labels used to train models can be difficu… (voir plus)lt or impossible to acquire. Self-supervision is a natural solution in settings with limited labeled data, but current self-supervised models for satellite data fail to take advantage of the characteristics of that data, including the temporal dimension (which is critical for many applications, such as monitoring crop growth) and availability of data from many complementary sensors (which can significantly improve a model's predictive performance). We present Presto (the Pretrained Remote Sensing Transformer), a model pre-trained on remote sensing pixel-timeseries data. By designing Presto specifically for remote sensing data, we can create a significantly smaller but performant model. Presto excels at a wide variety of globally distributed remote sensing tasks and performs competitively with much larger models while requiring far less compute. Presto can be used for transfer learning or as a feature extractor for simple models, enabling efficient deployment at scale.

2023-04-27

ArXiv (preprint)

Maximal Initial Learning Rates in Deep ReLU Networks

Gaurav Iyer

Boris Hanin

Training a neural network requires choosing a suitable learning rate, which involves a trade-off between speed and effectiveness of converge… (voir plus)nce. While there has been considerable theoretical and empirical analysis of how large the learning rate can be, most prior work focuses only on late-stage training. In this work, we introduce the maximal initial learning rate

2023-04-24

ICML.cc/2023/Conference (poster)

Semi-Supervised Object Detection for Agriculture

Gabriel Tseng

Krisztina Sinkovics

Tom Watsham

Thomas C. Walters

2023-01-26

AAAI.org/2023/Workshop/AIAFS (poster)

Bugs in the Data: How ImageNet Misrepresents Biodiversity

Alexandra Luccioni

ImageNet-1k is a dataset often used for benchmarking machine learning (ML) models and evaluating tasks such as image recognition and object … (voir plus)detection. Wild animals make up 27% of ImageNet-1k but, unlike classes representing people and objects, these data have not been closely scrutinized. In the current paper, we analyze the 13,450 images from 269 classes that represent wild animals in the ImageNet-1k validation set, with the participation of expert ecologists. We find that many of the classes are ill-defined or overlapping, and that 12% of the images are incorrectly labeled, with some classes having >90% of images incorrect. We also find that both the wildlife-related labels and images included in ImageNet-1k present significant geographical and cultural biases, as well as ambiguities such as artificial animals, multiple species in the same image, or the presence of humans. Our findings highlight serious issues with the extensive use of this dataset for evaluating ML systems, the use of such algorithms in wildlife-related tasks, and more broadly the ways in which ML datasets are commonly created and curated.

2023-01-01

AAAI (publié)

Deep Networks as Paths on the Manifold of Neural Representations

Richard D Lange

Devin Kwok

Jordan Kyle Matelsky

Xinyue Wang

Konrad Paul Kording

2023-01-01

TAG-ML (publié)

proceedings.mlr.press

General Purpose AI Systems in the AI Act: Trying to Fit a Square Peg Into a Round Hole

Claire Boine

2023-01-01

SSRN Electronic Journal (publié)