David Kanaa — accepted AI-conference papers

2024

Course Correcting Koopman Representations

Mahan Fathi, Clement Gehring, Jonathan Pilault, David Kanaa, Pierre-Luc Bacon, Ross Goroshin

ICLR 2024poster

Koopman representations aim to learn features of nonlinear dynamical systems (NLDS) which lead to linear dynamics in the latent space. Theoretically, such features can be used to simplify many problems in modeling and control of NLDS. In this work we study autoencoder formulations of this problem, a…

Cited by 2 Source ↗PDF ↗Scholar ↗

2022

Continuous-Time Meta-Learning with Forward Mode Differentiation

Tristan Deleu, David Kanaa, Leo Feng, Giancarlo Kerg, Yoshua Bengio, Guillaume Lajoie +1

ICLR 2022spotlight

Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learning (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-lea…

Cited by 26 Source ↗PDF ↗Scholar ↗