Portrait of David Rolnick

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

Research Topics

AI and Sustainability

AI for Science

Applied Machine Learning

Biodiversity

Building Energy Management Systems

Climate

Climate Change

Climate Change AI

Climate Modeling

Climate Science

Climate Variable Downscaling

Computer Vision

Conservation Technology

Energy Systems

Forest Monitoring

Machine Learning and Climate Change

Machine Learning for Physical Sciences

Machine Learning in Climate Modeling

Machine Learning Theory

Out-of-Distribution (OOD) Detection

Remote Sensing

Satellite Remote Sensing

Time Series Forecasting

Vegetation

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

Collaborating researcher

Benjamin Akera Binen

Collaborating Alumni - McGill University

Collaborating researcher - Cambridge University

Co-supervisor :

Julien Boussard

Postdoctorate - McGill University

Collaborating researcher - McGill University

Juan Sebastián Cañas

Collaborating researcher

Shahana Chatterjee

Collaborating researcher - N/A

Co-supervisor :

Master's Research - McGill University

Collaborating researcher - Leipzig University

Amna El-Mustafa

Collaborating researcher

Mohamed Elabbas

Collaborating researcher

Collaborating researcher

Independent visiting researcher - Politecnico di Milano

Independent visiting researcher

Sebastian Hickman

Collaborating researcher - Université de Montréal

Christina Humer

Collaborating researcher - Johannes Kepler University

Christina Isaicu Isaicu

Collaborating researcher - University of Amsterdam

Master's Research - McGill University

Julia Kaltenborn

PhD - McGill University

PhD - McGill University

Collaborating researcher

Vincent Le Falher

Independent visiting researcher - Université de Montréal

Collaborating researcher - University of East Anglia

Collaborating researcher

Juan Nathaniel Nathaniel

Collaborating researcher - Columbia university

jn2808@columbia.edu

Othmane Othmane

Master's Research - McGill University

Arthur Ouaknine

Postdoctorate - McGill University

Co-supervisor :

Étienne Laliberté

PhD - University of Waterloo

Co-supervisor :

Venkatesh Ramesh

Collaborating Alumni - Université de Montréal

Master's Research - McGill University

Collaborating researcher - Columbia university

Master's Research - McGill University

Luca Marie Schmidt

Collaborating researcher - University of Tübingen

luca.schmidt@uni-tuebingen.de

Collaborating researcher

seth.pratinav@gmail.com

Ilija Trajković

Collaborating researcher - Karlsruhe Institute of Technology

PhD - McGill University

Postdoctorate - Université de Montréal

Principal supervisor :

Collaborating researcher

anna.viklund@mila.quebec

Catherine Villeneuve

PhD - McGill University

Collaborating Alumni - McGill University

Publications

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 … (see more)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.

Hidden Hypergraphs, Error-Correcting Codes, and Critical Learning in Hopfield Networks

Christopher Hillar

Tenzin Chan

Rachel Taubman

In 1943, McCulloch and Pitts introduced a discrete recurrent neural network as a model for computation in brains. The work inspired breakthr… (see more)oughs such as the first computer design and the theory of finite automata. We focus on learning in Hopfield networks, a special case with symmetric weights and fixed-point attractor dynamics. Specifically, we explore minimum energy flow (MEF) as a scalable convex objective for determining network parameters. We catalog various properties of MEF, such as biological plausibility, and then compare to classical approaches in the theory of learning. Trained Hopfield networks can perform unsupervised clustering and define novel error-correcting coding schemes. They also efficiently find hidden structures (cliques) in graph theory. We extend this known connection from graphs to hypergraphs and discover n-node networks with robust storage of 2Ω(n1−ϵ) memories for any ϵ>0. In the case of graphs, we also determine a critical ratio of training samples at which networks generalize completely.

2021-11-11

Entropy (published)