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 de recherche - Cambridge University

Co-superviseur⋅e :

julien.boussard@mila.quebec

berkes.anais@mila.quebec

Postdoctorat - McGill

Michael Bunsen

Collaborateur·rice de recherche - McGill

michael.bunsen@mila.quebec

Shahana Chatterjee

Collaborateur·rice de recherche - N/A

Co-superviseur⋅e :

shahana.chatterjee@mila.quebec

Yuyan Chen

Doctorat - McGill

yuyan.chen@mila.quebec

Graham Clyne

Postdoctorat - McGill

graham.clyne@mila.quebec

Ruth Crasto

Doctorat - McGill

ruth.crasto@mila.quebec

othmane.echchabi@mila.quebec

Othmane Echchabi

Maîtrise recherche - McGill

Collaborateur·rice de recherche

amna.elmustafa@mila.quebec

mohamed.elabbas@mila.quebec

Mohamed Elabbas

Collaborateur·rice de recherche

jannik.endres@mila.quebec

Jannik Endres

Collaborateur·rice de recherche

jacopo.ghirri@mila.quebec

Jacopo Ghirri

Visiteur de recherche indépendant - Politecnico di Milano

Visiteur de recherche indépendant

paula.harder@mila.quebec

Collaborateur·rice de recherche - Johannes Kepler University

christina.humer@mila.quebec

Gaurav Iyer

Maîtrise recherche - McGill

gaurav.iyer@mila.quebec

julia.kaltenborn@mila.quebec

Julia Kaltenborn

Doctorat - McGill

vincent.lefalher@mila.quebec

Devin Kwok

Doctorat - McGill

devin.kwok@mila.quebec

Visiteur de recherche indépendant - Université de Montréal

Pierre-Louis Lemaire

Collaborateur·rice de recherche - Polytechnique Montréal

Superviseur⋅e principal⋅e :

Alex Hernández-García

pierre-louis.lemaire@mila.quebec

david.mickisch@mila.quebec

David Mickisch

Collaborateur·rice de recherche

Postdoctorat - McGill

Co-superviseur⋅e :

Étienne Laliberté

arthur.ouaknine@mila.quebec

Lena Podina

Collaborateur·rice de recherche - University of Waterloo

Co-superviseur⋅e :

elena.podina@mila.quebec

Marlena Reil

Maîtrise recherche - McGill

marlena.reil@mila.quebec

Rasha Saha

Maîtrise recherche - McGill

sulagna.saha@mila.quebec

luca.schmidt@uni-tuebingen.de

Luca Marie Schmidt

Collaborateur·rice de recherche - University of Tübingen

Visiteur de recherche indépendant - Karlsruhe Institute of Technology

hossein.shirali@mila.quebec

Wietze Suijker

Visiteur de recherche indépendant

wietze.suijker@gmail.com

ilija.trajkovic@mila.quebec

Ilija Trajković

Collaborateur·rice de recherche - Karlsruhe Institute of Technology

gabriel.tseng@mila.quebec

Gabriel Tseng

Doctorat - McGill

Donna Vakalis

Collaborateur·rice alumni - UdeM

Superviseur⋅e principal⋅e :

donna.vakalis@mila.quebec

Collaborateur·rice de recherche

anna.viklund@mila.quebec

catherine.villeneuve@mila.quebec

Catherine Villeneuve

Doctorat - McGill

mohamed.yebari@mila.quebec

Mohamed Yebari

Collaborateur·rice de recherche - Ecole Polytechnique Fédérale de Lausanne (EPFL)

Co-superviseur⋅e :

Loubna Benabbou

Shan Zhao

Collaborateur·rice de recherche - Technical University of Munich

zhaoshanuestc@gmail.com

Démocratiser l'accès aux données satellitaires grâce à l'IA

Billets de blogue

diagram illustrating how the AI foundation model for Earth observation, Galileo, works

21 octobre 2025

par

Gabriel Tseng

David Rolnick

Lire l'article

Publications

Hard-Constrained Deep Learning for Climate Downscaling

Paula Harder

Venkatesh Ramesh

Alex Hernández-García

Qidong Yang

Prasanna Sattegeri

D. Szwarcman

Campbell Watson

The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and … (voir plus)mitigation and to guide rapid responses to extreme events. Forecasting models are limited by computational costs and, therefore, often generate coarse-resolution predictions. Statistical downscaling, including super-resolution methods from deep learning, can provide an efficient method of upsampling low-resolution data. However, despite achieving visually compelling results in some cases, such models frequently violate conservation laws when predicting physical variables. In order to conserve physical quantities, here we introduce methods that guarantee statistical constraints are satisfied by a deep learning downscaling model, while also improving their performance according to traditional metrics. We compare different constraining approaches and demonstrate their applicability across different neural architectures as well as a variety of climate and weather data sets. Besides enabling faster and more accurate climate predictions through downscaling, we also show that our novel methodologies can improve super-resolution for satellite data and natural images data sets.

2022-12-31

Journal of Machine Learning Research (publié)

arxiv.org

Understanding the Evolution of Linear Regions in Deep Reinforcement Learning

Setareh Cohan

Nam Hee Gordon Kim

Michiel van de Panne

Policies produced by deep reinforcement learning are typically characterised by their learning curves, but they remain poorly understood in … (voir plus)many other respects. ReLU-based policies result in a partitioning of the input space into piecewise linear regions. We seek to understand how observed region counts and their densities evolve during deep reinforcement learning using empirical results that span a range of continuous control tasks and policy network dimensions. Intuitively, we may expect that during training, the region density increases in the areas that are frequently visited by the policy, thereby affording fine-grained control. We use recent theoretical and empirical results for the linear regions induced by neural networks in supervised learning settings for grounding and comparison of our results. Empirically, we find that the region density increases only moderately throughout training, as measured along fixed trajectories coming from the final policy. However, the trajectories themselves also increase in length during training, and thus the region densities decrease as seen from the perspective of the current trajectory. Our findings suggest that the complexity of deep reinforcement learning policies does not principally emerge from a significant growth in the complexity of functions observed on-and-around trajectories of the policy.

2022-10-30

NeurIPS.cc/2022/Conference (accepté)

Digitalization and the Anthropocene

Felix Creutzig

Daron Acemoglu

Xuemei Bai

Paul N. Edwards

Marie Josefine Hintz

Lynn H. Kaack

Siir Kilkis

Stefanie Kunkel

Amy Luers

Nikola Milojevic-Dupont

Dave Rejeski

Jürgen Renn

Christoph Rosol

Daniela Russ

Thomas Turnbull

Elena Verdolini

Felix Wagner

Charlie Wilson

Aicha Zekar … (voir 1 de plus)

Marius Zumwald

Great claims have been made about the benefits of dematerialization in a digital service economy. However, digitalization has historically i… (voir plus)ncreased environmental impacts at local and planetary scales, affecting labor markets, resource use, governance, and power relationships. Here we study the past, present, and future of digitalization through the lens of three interdependent elements of the Anthropocene: ( a) planetary boundaries and stability, ( b) equity within and between countries, and ( c) human agency and governance, mediated via ( i) increasing resource efficiency, ( ii) accelerating consumption and scale effects, ( iii) expanding political and economic control, and ( iv) deteriorating social cohesion. While direct environmental impacts matter, the indirect and systemic effects of digitalization are more profoundly reshaping the relationship between humans, technosphere and planet. We develop three scenarios: planetary instability, green but inhumane, and deliberate for the good. We conclude with identifying leverage points that shift human–digital–Earth interactions toward sustainability.

2022-09-01

Annual Review Environment and Resources (publié)

A portrait of the different configurations between digitally-enabled innovations and climate governance

Pierre J. C. Chuard

Jennifer Garard

Karsten A. Schulz

Nilushi Kumarasinghe

Damon Matthews

2022-07-31

Earth System Governance (publié)

Neural Networks as Paths through the Space of Representations

Richard D Lange

Jordan Kyle Matelsky

Xinyue Wang

Devin Kwok

Konrad Paul Kording

2022-06-21

ArXiv (prépublication)

Clustering units in neural networks: upstream vs downstream information

Richard D Lange

Konrad Paul Kording

It has been hypothesized that some form of"modular"structure in artificial neural networks should be useful for learning, compositionality, … (voir plus)and generalization. However, defining and quantifying modularity remains an open problem. We cast the problem of detecting functional modules into the problem of detecting clusters of similar-functioning units. This begs the question of what makes two units functionally similar. For this, we consider two broad families of methods: those that define similarity based on how units respond to structured variations in inputs ("upstream"), and those based on how variations in hidden unit activations affect outputs ("downstream"). We conduct an empirical study quantifying modularity of hidden layer representations of simple feedforward, fully connected networks, across a range of hyperparameters. For each model, we quantify pairwise associations between hidden units in each layer using a variety of both upstream and downstream measures, then cluster them by maximizing their"modularity score"using established tools from network science. We find two surprising results: first, dropout dramatically increased modularity, while other forms of weight regularization had more modest effects. Second, although we observe that there is usually good agreement about clusters within both upstream methods and downstream methods, there is little agreement about the cluster assignments across these two families of methods. This has important implications for representation-learning, as it suggests that finding modular representations that reflect structure in inputs (e.g. disentanglement) may be a distinct goal from learning modular representations that reflect structure in outputs (e.g. compositionality).

2022-06-12

TMLR (accepté)

On Neural Architecture Inductive Biases for Relational Tasks

Current deep learning approaches have shown good in-distribution generalization performance, but struggle with out-of-distribution generaliz… (voir plus)ation. This is especially true in the case of tasks involving abstract relations like recognizing rules in sequences, as we find in many intelligence tests. Recent work has explored how forcing relational representations to remain distinct from sensory representations, as it seems to be the case in the brain, can help artificial systems. Building on this work, we further explore and formalize the advantages afforded by 'partitioned' representations of relations and sensory details, and how this inductive bias can help recompose learned relational structure in newly encountered settings. We introduce a simple architecture based on similarity scores which we name Compositional Relational Network (CoRelNet). Using this model, we investigate a series of inductive biases that ensure abstract relations are learned and represented distinctly from sensory data, and explore their effects on out-of-distribution generalization for a series of relational psychophysics tasks. We find that simple architectural choices can outperform existing models in out-of-distribution generalization. Together, these results show that partitioning relational representations from other information streams may be a simple way to augment existing network architectures' robustness when performing out-of-distribution relational computations.

2022-06-08

ArXiv (prépublication)

arxiv.org

Aligning artificial intelligence with climate change mitigation

Lynn H. Kaack

Priya L. Donti

Emma Strubell

George Kamiya

Felix Creutzig

2022-05-31

Nature Climate Change (inconnu)

Inductive Biases for Relational Tasks

Blake Aaron Richards

Current deep learning approaches have shown good in-distribution performance but struggle in out-of-distribution settings. This is especiall… (voir plus)y true in the case of tasks involving abstract relations like recognizing rules in sequences, as required in many intelligence tests. In contrast, our brains are remarkably flexible at such tasks, an attribute that is likely linked to anatomical constraints on computations. Inspired by this, recent work has explored how enforcing that relational representations remain distinct from sensory representations can help artificial systems. Building on this work, we further explore and formalize the advantages afforded by ``partitioned'' representations of relations and sensory details. We investigate inductive biases that ensure abstract relations are learned and represented distinctly from sensory data across several neural network architectures and show that they outperform existing architectures on out-of-distribution generalization for various relational tasks. These results show that partitioning relational representations from other information streams may be a simple way to augment existing network architectures' robustness when performing relational computations.

2022-03-24

ICLR.cc/2022/Workshop/OSC (poster)

TIML: Task-Informed Meta-Learning for Agriculture

Gabriel Tseng

Hannah Kerner

Labeled datasets for agriculture are extremely spatially imbalanced. When developing algorithms for data-sparse regions, a natural approach … (voir plus)is to use transfer learning from data-rich regions. While standard transfer learning approaches typically leverage only direct inputs and outputs, geospatial imagery and agricultural data are rich in metadata that can inform transfer learning algorithms, such as the spatial coordinates of data-points or the class of task being learned. We build on previous work exploring the use of meta-learning for agricultural contexts in data-sparse regions and introduce task-informed meta-learning (TIML), an augmentation to model-agnostic meta-learning which takes advantage of task-specific metadata. We apply TIML to crop type classification and yield estimation, and find that TIML significantly improves performance compared to a range of benchmarks in both contexts, across a diversity of model architectures. While we focus on tasks from agriculture, TIML could offer benefits to any meta-learning setup with task-specific metadata, such as classification of geo-tagged images and species distribution modelling.

2022-02-03

ArXiv (prépublication)

arxiv.org

Deep ReLU Networks Preserve Expected Length

Boris Hanin

Ryan Jeong

Assessing the complexity of functions computed by a neural network helps us understand how the network will learn and generalize. One natura… (voir plus)l measure of complexity is how the network distorts length - if the network takes a unit-length curve as input, what is the length of the resulting curve of outputs? It has been widely believed that this length grows exponentially in network depth. We prove that in fact this is not the case: the expected length distortion does not grow with depth, and indeed shrinks slightly, for ReLU networks with standard random initialization. We also generalize this result by proving upper bounds both for higher moments of the length distortion and for the distortion of higher-dimensional volumes. These theoretical results are corroborated by our experiments.

2022-01-27

ICLR.cc/2022/Conference (poster)

Generating physically-consistent high-resolution climate data with hard-constrained neural networks

Paula Harder

Qidong Yang

Venkatesh Ramesh

Prasanna Sattegeri

Alex Hernández-García

Campbell Watson

D. Szwarcman

The availability of reliable, high-resolution climate and weather data is important to inform long-term decisions on climate adaptation and … (voir plus)mitigation and to guide rapid responses to extreme events. Forecasting models are limited by computational costs and therefore often can only make coarse resolution predictions. Statistical downscaling can provide an efficient method of upsampling low-resolution data. In this field, deep learning has been applied successfully, often us-ing image super-resolution methods from computer vision. Despite achieving visually compelling results in some cases, such models often violate conservation laws when predicting physical variables. In order to conserve important physical quantities, we develop methods that guarantee physical constraints are satisfied by a deep downscaling model while also increasing their performance according to traditional metrics. We introduce two ways of constraining the network: A renor-malization layer added to the end of the neural network and a successive approach that scales with increasing upsampling factors. We show the applicability of our methods across different popular architectures and upsampling factors using ERA5 reanalysis data.

2021-12-31

arXiv.org (prépublication)