Portrait of David Rolnick

David Rolnick

Core Academic Member
Canada CIFAR AI Chair
Assistant Professor, McGill University, School of Computer Science
Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research

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

Postdoctorate - Université de Montréal
Principal supervisor :
Collaborating researcher - Université Paris-Saclay
Co-supervisor :
Collaborating researcher
Collaborating researcher
Collaborating researcher
Collaborating researcher
Collaborating researcher
Co-supervisor :
Collaborating researcher
Research Intern - Johannes Kepler University
Postdoctorate - Université de Montréal
Principal supervisor :
Research Intern - Université de Montréal
Master's Research - McGill University
Collaborating researcher - Karlsruhe Institute of Technology
Collaborating researcher
Research Intern - Osnabrueck university
Master's Research - McGill University
Collaborating researcher - McGill University
Collaborating researcher - The University of Dresden, Helmholtz Centre for Environmental Research Leipzig
Collaborating researcher - National Observatory of Athens
Collaborating researcher
Collaborating researcher - KU Leuven
Research Intern - Cambridge University
Collaborating researcher
Co-supervisor :
Postdoctorate - McGill University
PhD - Université de Montréal
Collaborating researcher - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)
Co-supervisor :
Master's Research - McGill University

Publications

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 … (see more)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.
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.