David Rolnick

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

Benjamin Akera Binen

Master's Research - McGill University

Collaborating Alumni - Université de Montréal

Mohit Anand

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

Ayush Ayush Prasad

Collaborating researcher

Nikolaos Ioannis Bountos

Collaborating researcher - National Observatory of Athens

Collaborating researcher

Michael Bunsen

Collaborating researcher - McGill University

Juan Sebastián Cañas

Collaborating researcher

Collaborating researcher - KU Leuven

Yuyan Chen

Master's Research - McGill University

Eya Cherif

Research Intern

Collaborating Alumni

Collaborating researcher - Université Paris-Saclay

Co-supervisor :

Amna El-Mustafa

Collaborating researcher

Paula Harder

Collaborating researcher

Alex Hernandez-Garcia

Postdoctorate - Université de Montréal

Principal supervisor :

Collaborating researcher - Université de Montréal

Christina Humer

Research Intern - Johannes Kepler University

Gaurav Iyer

Master's Research - McGill University

Julia Kaltenborn

PhD - McGill University

Devin Kwok

PhD - McGill University

Vanessa Mac

Collaborating researcher - University of Waterloo

David Alexandre Mickisch

Collaborating researcher

Chandni Nagda

Collaborating researcher

Felix Andreas Nahrstedt

Research Intern - Université de Montréal

Arthur Ouaknine

Postdoctorate - McGill University

Co-supervisor :

Lena Podina

PhD - University of Waterloo

Co-supervisor :

Venkatesh Ramesh

PhD - Université de Montréal

Ali Ramlaoui

Collaborating researcher

Marlena Reil

Master's Research - Osnabrueck university

Theo Saulus

Collaborating researcher

Co-supervisor :

Raesetje Sefala

PhD - McGill University

Pratinav Seth

Collaborating researcher

seth.pratinav@gmail.com

Collaborating researcher

Co-supervisor :

Ilija Trajković

Collaborating researcher - Karlsruhe Institute of Technology

Gabriel Tseng

PhD - McGill University

Donna Vakalis

Postdoctorate - Université de Montréal

Principal supervisor :

Collaborating researcher

Todosijevic Viktor Todosijevic

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

Co-supervisor :

Catherine Villeneuve

PhD - McGill University

Tiffany Vlaar

Postdoctorate - McGill University

Christina Winkler

Collaborating researcher

Qidong Yang

Collaborating researcher

qidong.yang@mila.quebec

Publications

Tree semantic segmentation from aerial image time series

Venkatesh Ramesh

Arthur Ouaknine

2024-07-18

ArXiv (preprint)

Stealing part of a production language model

Nicholas Carlini

Daniel Paleka

Krishnamurthy Dj Dvijotham

Thomas Steinke

Jonathan Hayase

A. Feder Cooper

Katherine Lee

Matthew Jagielski

Milad Nasr

Arthur Conmy

Eric Wallace

Florian Tramèr

We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like … (see more)OpenAI's ChatGPT or Google's PaLM-2. Specifically, our attack recovers the embedding projection layer (up to symmetries) of a transformer model, given typical API access. For under \\

2024-07-08

Proceedings of the 41st International Conference on Machine Learning (published)

Improving Molecular Modeling with Geometric GNNs: an Empirical Study

Ali Ramlaoui

Théo Saulus

Basile Terver

Victor Schmidt

Fragkiskos D. Malliaros

Alexandre AGM Duval

2024-06-17

ICML.cc/2024/Workshop/ML4LMS (poster)

Gintare Karolina Dziugaite

Linear Weight Interpolation Leads to Transient Performance Gains

Gaurav Iyer

2024-06-16

ICML.cc/2024/Workshop/HiLD (poster)

The Butterfly Effect: Tiny Perturbations Cause Neural Network Training to Diverge

Gül Sena Altıntaş

Devin Kwok

Neural network training begins with a chaotic phase in which the network is sensitive to small perturbations, such as those caused by stocha… (see more)stic gradient descent (SGD). This sensitivity can cause identically initialized networks to diverge both in parameter space and functional similarity. However, the exact degree to which networks are sensitive to perturbation, and the sensitivity of networks as they transition out of the chaotic phase, is unclear. To address this uncertainty, we apply a controlled perturbation at a single point in training time and measure its effect on otherwise identical training trajectories. We find that both the

2024-06-16

ICML.cc/2024/Workshop/HiLD (poster)

Position: Application-Driven Innovation in Machine Learning

Alan Aspuru-Guzik

Sara Beery

Bistra Dilkina

Priya L. Donti

Marzyeh Ghassemi

Hannah Kerner

Claire Monteleoni

Esther Rolf

Milind Tambe

Adam White

2024-05-01

ICML.cc/2024/Conference (poster)

proceedings.mlr.press

Simultaneous linear connectivity of neural networks modulo permutation

Ekansh Sharma

Devin Kwok

Tom Denton

Daniel M. Roy

Gintare Karolina Dziugaite

2024-04-09

ArXiv (preprint)

Application-Driven Innovation in Machine Learning

Alan Aspuru-Guzik

Sara Beery

Bistra N. Dilkina

Priya L. Donti

Marzyeh Ghassemi

Hannah Kerner

Claire Monteleoni

Esther Rolf

Milind Tambe

Adam White

As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly i… (see more)mportant. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.

2024-03-26

ArXiv (preprint)

Predicting Species Occurrence Patterns from Partial Observations

Hager Radi

Mélisande Teng

To address the interlinked biodiversity and climate crises, we need an understanding of where species occur and how these patterns are chang… (see more)ing. However, observational data on most species remains very limited, and the amount of data available varies greatly between taxonomic groups. We introduce the problem of predicting species occurrence patterns given (a) satellite imagery, and (b) known information on the occurrence of other species. To evaluate algorithms on this task, we introduce SatButterfly, a dataset of satellite images, environmental data and observational data for butterflies, which is designed to pair with the existing SatBird dataset of bird observational data. To address this task, we propose a general model, R-Tran, for predicting species occurrence patterns that enables the use of partial observational data wherever found. We find that R-Tran outperforms other methods in predicting species encounter rates with partial information both within a taxon (birds) and across taxa (birds and butterflies). Our approach opens new perspectives to leveraging insights from species with abundant data to other species with scarce data, by modelling the ecosystems in which they co-occur.

2024-03-26

ArXiv (preprint)

Stealing Part of a Production Language Model

Nicholas Carlini

Daniel Paleka

Krishnamurthy Dvijotham

Thomas Steinke

Jonathan Hayase

A. Feder Cooper

Katherine Lee

Matthew Jagielski

Milad Nasr

Arthur Conmy

Eric Wallace

Florian Tramèr

2024-03-11

ArXiv (preprint)

Tackling Climate Change with Machine Learning: Fostering the Maturity of ML Applications for Climate Change

Shiva Madadkhani

Olivia Mendivil Ramos

Millie Chapman

Jesse Dunietz

Arthur Ouaknine

2024-03-08

ICLR.cc/2024/Workshop_Proposals (published)

Gintare Karolina Dziugaite

Dataset Difficulty and the Role of Inductive Bias

Devin Kwok

Nikhil Anand

Jonathan Frankle

Motivated by the goals of dataset pruning and defect identification, a growing body of methods have been developed to score individual examp… (see more)les within a dataset. These methods, which we call"example difficulty scores", are typically used to rank or categorize examples, but the consistency of rankings between different training runs, scoring methods, and model architectures is generally unknown. To determine how example rankings vary due to these random and controlled effects, we systematically compare different formulations of scores over a range of runs and model architectures. We find that scores largely share the following traits: they are noisy over individual runs of a model, strongly correlated with a single notion of difficulty, and reveal examples that range from being highly sensitive to insensitive to the inductive biases of certain model architectures. Drawing from statistical genetics, we develop a simple method for fingerprinting model architectures using a few sensitive examples. These findings guide practitioners in maximizing the consistency of their scores (e.g. by choosing appropriate scoring methods, number of runs, and subsets of examples), and establishes comprehensive baselines for evaluating scores in the future.

2024-01-03

ArXiv (preprint)