Courtney Paquette
About
Appointed Canada CIFAR AI Chair – 2020
Courtney Paquette is a Canada CIFAR AI Chair at Mila, an assistant professor at the department of mathematics and statistics at McGill University, and a research scientist at Google Brain.
Paquette’s research focuses on designing and analyzing algorithms for large-scale optimization problems, motivated by applications in data science. Some of the techniques Paquette uses in her research include a variety of fields including probability, complexity theory, and convex and nonsmooth analysis.
Awards
- Alfred P. Sloan Fellowship, 2024
- Tanzi-Egerton Fellowship Award, 2016
- Excellence in Teaching Award, University of Washington Mathematics Department, 2012
Relevant Publications
- Collins-Woodfin, E., Paquette, C., Paquette, E., & Seroussi, I. (2023). Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models.
- Paquette, C., Paquette, E., Adlam, B., & Pennington, J. (2022). Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties.
Paquette, C., Lee, K., Pedregosa, F., & Paquette, E. (2021). SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality.
Paquette, C., & Paquette, E. (2021). Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models.
Davis, D., Drusvyatskiy, D., & Paquette, C. (2020). The nonsmooth landscape of phase retrieval. IMA Journal of Numerical Analysis, 40(4), 2652-2695.