Portrait de David Kanaa

David Kanaa

Alumni
Google Scholar

Publications

Course Correcting Koopman Representations
Mahan Fathi
Clement Gehring
Jonathan Pilault
David Kanaa
Pierre-Luc Bacon
Ross Goroshin
2024-01-16
ICLR.cc/2024/Conference (poster)
doi.org
openreview.net
Continuous-Time Meta-Learning with Forward Mode Differentiation
Tristan Deleu
David Kanaa
Leo Feng
Giancarlo Kerg
Yoshua Bengio
Guillaume Lajoie
Pierre-Luc Bacon
Drawing inspiration from gradient-based meta-learning methods with infinitely small gradient steps, we introduce Continuous-Time Meta-Learni… (voir plus)ng (COMLN), a meta-learning algorithm where adaptation follows the dynamics of a gradient vector field. Specifically, representations of the inputs are meta-learned such that a task-specific linear classifier is obtained as a solution of an ordinary differential equation (ODE). Treating the learning process as an ODE offers the notable advantage that the length of the trajectory is now continuous, as opposed to a fixed and discrete number of gradient steps. As a consequence, we can optimize the amount of adaptation necessary to solve a new task using stochastic gradient descent, in addition to learning the initial conditions as is standard practice in gradient-based meta-learning. Importantly, in order to compute the exact meta-gradients required for the outer-loop updates, we devise an efficient algorithm based on forward mode differentiation, whose memory requirements do not scale with the length of the learning trajectory, thus allowing longer adaptation in constant memory. We provide analytical guarantees for the stability of COMLN, we show empirically its efficiency in terms of runtime and memory usage, and we illustrate its effectiveness on a range of few-shot image classification problems.
2022-01-28
ICLR.cc/2022/Conference (spotlight)
doi.org
openreview.net
Simple Video Generation using Neural ODEs
David Kanaa
Vikram Voleti
Samira Ebrahimi Kahou
Chris Pal
Despite having been studied to a great extent, the task of conditional generation of sequences of frames, or videos, remains extremely chall… (voir plus)enging. It is a common belief that a key step towards solving this task resides in modelling accurately both spatial and temporal information in video signals. A promising direction to do so has been to learn latent variable models that predict the future in latent space and project back to pixels, as suggested in recent literature. Following this line of work and building on top of a family of models introduced in prior work, Neural ODE, we investigate an approach that models time-continuous dynamics over a continuous latent space with a differential equation with respect to time. The intuition behind this approach is that these trajectories in latent space could then be extrapolated to generate video frames beyond the time steps for which the model is trained. We show that our approach yields promising results in the task of future frame prediction on the Moving MNIST dataset with 1 and 2 digits.
2021-09-07
ArXiv (prépublication)
arxiv.org
arxiv.org