Portrait de David Rolnick

David Rolnick

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur adjoint, McGill University, École d'informatique
Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle

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

Postdoctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Collaborateur·rice de recherche - Université Paris-Saclay
Co-superviseur⋅e :
Collaborateur·rice de recherche
Collaborateur·rice de recherche
Collaborateur·rice de recherche
Collaborateur·rice de recherche
Collaborateur·rice de recherche
Co-superviseur⋅e :
Maîtrise recherche - McGill University
Collaborateur·rice de recherche
Postdoctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Stagiaire de recherche
Stagiaire de recherche - Université de Montréal
Maîtrise recherche - McGill University
Stagiaire de recherche - Université de Montréal
Collaborateur·rice de recherche - Karlsruhe Institute of Technology
Collaborateur·rice de recherche
Collaborateur·rice alumni
Maîtrise recherche - McGill University
Collaborateur·rice de recherche - McGill University
Collaborateur·rice de recherche - The University of Dresden, Helmholtz Centre for Environmental Research Leipzig
Collaborateur·rice de recherche - National Observatory of Athens
Maîtrise recherche - McGill University
Collaborateur·rice de recherche
Collaborateur·rice de recherche - KU Leuven
Stagiaire de recherche - Cambridge University
Collaborateur·rice de recherche
Co-superviseur⋅e :
Postdoctorat - McGill University
Doctorat - Université de Montréal
Collaborateur·rice de recherche - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)
Co-superviseur⋅e :
Maîtrise recherche - McGill University

Publications

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 … (voir plus)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 \\
Simultaneous linear connectivity of neural networks modulo permutation
Ekansh Sharma
Devin Kwok
Tom Denton
Daniel M. Roy
Application-Driven Innovation in Machine Learning
Alán 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… (voir plus)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.
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… (voir plus)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.
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
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
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… (voir plus)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.
A landmark environmental law looks ahead
Robert L. Fischman
J. B. Ruhl
Brenna R. Forester
Tanya M. Lama
Marty Kardos
Grethel Aguilar Rojas
Nicholas A. Robinson
Patrick D. Shirey
Gary A. Lamberti
Amy W. Ando
Stephen Palumbi
Michael Wara
Mark W. Schwartz
Matthew A. Williamson
Tanya Berger-Wolf
Sara Beery
Justin Kitzes
David Thau
Devis Tuia … (voir 8 de plus)
Daniel Rubenstein
Caleb R. Hickman
Julie Thorstenson
Gregory E. Kaebnick
James P. Collins
Athmeya Jayaram
Thomas Deleuil
Ying Zhao
FoMo-Bench: a multi-modal, multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models
Nikolaos Ioannis Bountos
Arthur Ouaknine
Towards Causal Representations of Climate Model Data
Julien Boussard
Chandni Nagda
Julia Kaltenborn
Charlotte Emilie Elektra Lange
Philippe Brouillard
Yaniv Gurwicz
Peer Nowack
Climate models, such as Earth system models (ESMs), are crucial for simulating future climate change based on projected Shared Socioeconomic… (voir plus) Pathways (SSP) greenhouse gas emissions scenarios. While ESMs are sophisticated and invaluable, machine learning-based emulators trained on existing simulation data can project additional climate scenarios much faster and are computationally efficient. However, they often lack generalizability and interpretability. This work delves into the potential of causal representation learning, specifically the \emph{Causal Discovery with Single-parent Decoding} (CDSD) method, which could render climate model emulation efficient \textit{and} interpretable. We evaluate CDSD on multiple climate datasets, focusing on emissions, temperature, and precipitation. Our findings shed light on the challenges, limitations, and promise of using CDSD as a stepping stone towards more interpretable and robust climate model emulation.
SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
Mélisande Teng
Amna Elmustafa
Benjamin Akera
Hager Radi
Biodiversity is declining at an unprecedented rate, impacting ecosystem services necessary to ensure food, water, and human health and well-… (voir plus)being. Understanding the distribution of species and their habitats is crucial for conservation policy planning. However, traditional methods in ecology for species distribution models (SDMs) generally focus either on narrow sets of species or narrow geographical areas and there remain significant knowledge gaps about the distribution of species. A major reason for this is the limited availability of data traditionally used, due to the prohibitive amount of effort and expertise required for traditional field monitoring. The wide availability of remote sensing data and the growing adoption of citizen science tools to collect species observations data at low cost offer an opportunity for improving biodiversity monitoring and enabling the modelling of complex ecosystems. We introduce a novel task for mapping bird species to their habitats by predicting species encounter rates from satellite images, and present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird, considering summer (breeding) and winter seasons. We also provide a dataset in Kenya representing low-data regimes. We additionally provide environmental data and species range maps for each location. We benchmark a set of baselines on our dataset, including SOTA models for remote sensing tasks. SatBird opens up possibilities for scalably modelling properties of ecosystems worldwide.
OpenForest: A data catalogue for machine learning in forest monitoring
Arthur Ouaknine
Teja Kattenborn
Etienne Lalibert'e