David Rolnick

Core Academic Member

drolnick@mila.quebec

Canada CIFAR AI Chair

Assistant Professor, McGill University, School of Computer Science

Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research

Website

Google Scholar

Biography

David Rolnick is an assistant professor at McGill University’s School of Computer Science, a core academic member of Mila – Quebec Artificial Intelligence Institute and holds a Canada CIFAR AI Chair. Rolnick’s work focuses on applications of machine learning to help address climate change. He is the co-founder and chair of Climate Change AI, and scientific co-director of Sustainability in the Digital Age. After completing his PhD in applied mathematics at the Massachusetts Institute of Technology (MIT), he was a NSF Mathematical Sciences Postdoctoral Research Fellow, an NSF Graduate Research Fellow and a Fulbright Scholar. He was named to MIT Technology Review’s “35 Innovators Under 35” in 2021.

Current Students

Alex Hernandez-Garcia

Postdoctorate - Université de Montréal

Principal supervisor :

Collaborating researcher - Université Paris-Saclay

Co-supervisor :

Yoshua Bengio

alexandre.duval@mila.quebec

Website

Ali Ramlaoui

Collaborating researcher

ali.ramlaoui@mila.quebec

Github

Amna El-Mustafa

Collaborating researcher

amna.elmustafa@mila.quebec

Anna Viklund

Collaborating researcher

anna.viklund@mila.quebec

Github

Arthur Ouaknine

Postdoctorate - McGill University

arthur.ouaknine@mila.quebec

Collaborating researcher

ayush.prasad@mila.quebec

Basile Terver

Collaborating researcher

Co-supervisor :

Yoshua Bengio

basile.terver@mila.quebec

Benjamin Akera Binen

Master's Research - McGill University

PhD - McGill University

catherine.villeneuve@mila.quebec

Github

Chandni Nagda

Collaborating researcher

chandni.nagda@mila.quebec

Christina Winkler

Collaborating researcher

christina.winkler@mila.quebec

Research Intern - Johannes Kepler University

christina.humer@mila.quebec

Website

Github

Google Scholar

David Alexandre Mickisch

Collaborating researcher

david.mickisch@mila.quebec

Github

Devin Kwok

PhD - McGill University

devin.kwok@mila.quebec

Postdoctorate - Université de Montréal

Principal supervisor :

Yoshua Bengio

donna.vakalis@mila.quebec

Github

Google Scholar

Eya Cherif

Research Intern

eya.cherif@mila.quebec

Felix Andreas Nahrstedt

Research Intern - Université de Montréal

felix-andreas.nahrstedt@mila.quebec

Website

Fagner Cunha

Collaborating Alumni

fagner.cunha@mila.quebec

PhD - McGill University

gabriel.tseng@mila.quebec

Website

Github

Gaurav Iyer

Master's Research - McGill University

gaurav.iyer@mila.quebec

Google Scholar

Gül Sena Altıntaş

Research Intern - Université de Montréal

gul-sena.altintas@mila.quebec

Collaborating researcher - Karlsruhe Institute of Technology

ilija.trajkovic@mila.quebec

Github

Juan Sebastián Cañas

Collaborating researcher

juan-sebastian.canas-silva@mila.quebec

PhD - McGill University

julia.kaltenborn@mila.quebec

Collaborating researcher

julien.boussard@mila.quebec

Marlena Reil

Research Intern - Osnabrueck university

marlena.reil@mila.quebec

Github

Mehrab Hamidi

Master's Research - McGill University

mehrab.hamidi@mila.quebec

Github

Google Scholar

Michael Bunsen

Collaborating researcher - McGill University

michael.bunsen@mila.quebec

Website

Github

Mohit Anand

Collaborating researcher - The University of Dresden, Helmholtz Centre for Environmental Research Leipzig

mohit.anand@mila.quebec

Github

Nikolaos Ioannis Bountos

Collaborating researcher - National Observatory of Athens

nikolaos.bountos@mila.quebec

Collaborating researcher

paula.harder@mila.quebec

Collaborating researcher

pratinav.seth@learner.manipal.edu

Website

Github

Google Scholar

Qidong Yang

Collaborating researcher

qidong.yang@mila.quebec

Raesetje Sefala

PhD - McGill University

raesetje.sefala@mila.quebec

Website

Ruben Cartuyvels

Collaborating researcher - KU Leuven

ruben.cartuyvels@mila.quebec

Sebastian Hickman

Research Intern - Cambridge University

sebastian.hickman@mila.quebec

Theo Saulus

Collaborating researcher

Co-supervisor :

Yoshua Bengio

theo.saulus@mila.quebec

Tiffany Vlaar

Postdoctorate - McGill University

tiffany.vlaar@mila.quebec

Google Scholar

Venkatesh Ramesh

PhD - Université de Montréal

venkatesh.ramesh@mila.quebec

Todosijevic Viktor Todosijevic

Collaborating researcher - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)

Co-supervisor :

Yoshua Bengio

viktor.todosijevic@mila.quebec

Github

Yuyan Chen

Master's Research - McGill University

yuyan.chen@mila.quebec

Website

Github

Publications

Bugs in the Data: How ImageNet Misrepresents Biodiversity

Alexandra Luccioni

David Rolnick

ImageNet-1k is a dataset often used for benchmarking machine learning (ML) models and evaluating tasks such as image recognition and object … (see more)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 (published)

doi.org

arxiv.org

Deep Networks as Paths on the Manifold of Neural Representations

Richard D Lange

Devin Kwok

Jordan Kyle Matelsky

Xinyue Wang

David Rolnick

Konrad Paul Kording

2023-01-01

TAG-ML (published)

proceedings.mlr.press

openreview.net

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

Claire Boine

David Rolnick

2023-01-01

SSRN Electronic Journal (published)

doi.org

Normalization Layers Are All That Sharpness-Aware Minimization Needs

Maximilian Mueller

Tiffany Joyce Vlaar

David Rolnick

Matthias Hein

Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in va… (see more)rious settings. In this work we show that perturbing only the affine normalization parameters (typically comprising 0.1% of the total parameters) in the adversarial step of SAM can outperform perturbing all of the parameters.This finding generalizes to different SAM variants and both ResNet (Batch Normalization) and Vision Transformer (Layer Normalization) architectures. We consider alternative sparse perturbation approaches and find that these do not achieve similar performance enhancement at such extreme sparsity levels, showing that this behaviour is unique to the normalization layers. Although our findings reaffirm the effectiveness of SAM in improving generalization performance, they cast doubt on whether this is solely caused by reduced sharpness.

openreview.net

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

David Rolnick

Christoph Rosol

Daniela Russ

Thomas Turnbull

Elena Verdolini

Felix Wagner

Charlie Wilson

Aicha Zekar … (see 1 more)

Marius Zumwald

Great claims have been made about the benefits of dematerialization in a digital service economy. However, digitalization has historically i… (see more)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. Expected final online publication date for the Annual Review of Environment and Resources, Volume 47 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

2022-09-02

Annual Review Environment and Resources (published)

doi.org

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

Pierre J. C. Chuard

Jennifer Garard

Karsten A. Schulz

Nilushi Kumarasinghe

David Rolnick

Damon Matthews

2022-08-01

Earth System Governance (published)

doi.org

Neural Networks as Paths through the Space of Representations

Richard D Lange

Devin Kwok

Jordan Kyle Matelsky

Xinyue Wang

David Rolnick

Konrad Paul Kording

2022-06-22

ArXiv (preprint)

doi.org

openreview.net

Clustering units in neural networks: upstream vs downstream information

Richard D Lange

David Rolnick

Konrad Paul Kording

It has been hypothesized that some form of"modular"structure in artificial neural networks should be useful for learning, compositionality, … (see more)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).

2022-06-13

TMLR (accepted)

doi.org

openreview.net

On Neural Architecture Inductive Biases for Relational Tasks

Giancarlo Kerg

Sarthak Mittal

Current deep learning approaches have shown good in-distribution generalization performance, but struggle with out-of-distribution generaliz… (see more)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.

2022-06-09

ArXiv (preprint)

doi.org

arxiv.org

Aligning artificial intelligence with climate change mitigation

Lynn H. Kaack

Priya L. Donti

Emma Strubell

George Yoshito Kamiya

Felix Creutzig

David Rolnick

2022-06-01

Nature Climate Change (published)

doi.org

Inductive Biases for Relational Tasks

Giancarlo Kerg

Sarthak Mittal

Current deep learning approaches have shown good in-distribution performance but struggle in out-of-distribution settings. This is especiall… (see more)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.

2022-03-25

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

openreview.net

Tackling Climate Change with Machine Learning

David Rolnick

Priya L. Donti

Lynn H. Kaack

Kelly Kochanski

Alexandre Lacoste

Kris Sankaran

Andrew Slavin Ross

Nikola Milojevic-Dupont

Natasha Jaques

Anna Waldman-Brown

Alexandra Luccioni

Tegan Maharaj

Evan David Sherwin

S. Karthik Mukkavilli

Konrad Paul Kording

Carla P. Gomes

Andrew Y. Ng

Demis Hassabis

John C. Platt

Felix Creutzig … (see 2 more)

Jennifer T Chayes

Yoshua Bengio

Climate change is one of the greatest challenges facing humanity, and we, as machine learning (ML) experts, may wonder how we can help. Here… (see more) we describe how ML can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by ML, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the ML community to join the global effort against climate change.

2022-02-07

ACM Computing Surveys (published)

doi.org

arxiv.org

AI Research Driven by Real-World Problems

AI Policy Compass

Student Life and Resources

David Rolnick

Biography

Current Students

Publications

AI Research Driven by Real-World Problems

AI Policy Compass

Student Life and Resources

Popular keywords:

David Rolnick

Biography

Current Students

Publications