260 citations · 657 across the 30 of their papers we have counts for
12 papers · 1 filter
Neural Koopman prior for data assimilation
Anthony Frion, Lucas Drumetz, Mauro Dalla Mura +2
With the increasing availability of large scale datasets, computational power and tools like automatic differentiation and expressive neural network architectures, sequential data…
Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data
Anthony Frion, Lucas Drumetz, Mauro Dalla Mura +2
Over the last few years, several works have proposed deep learning architectures to learn dynamical systems from observation data with no or little knowledge of the underlying phys…
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
Clément Bonet, Benoît Malézieux, Alain Rakotomamonjy +4
When dealing with electro or magnetoencephalography records, many supervised prediction tasks are solved by working with covariance matrices to summarize the signals. Learning with…
Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections
Clément Bonet, Laetitia Chapel, Lucas Drumetz +1
It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces. Consequently, many tools of machine lear…
Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings
Aymane Abdali, Vincent Gripon, Lucas Drumetz +1
We consider a novel formulation of the problem of Active Few-Shot Classification (AFSC) where the objective is to classify a small, initially unlabeled, dataset given a very restra…
Turning Normalizing Flows into Monge Maps with Geodesic Gaussian Preserving Flows
Guillaume Morel, Lucas Drumetz, Simon Benaïchouche +2
Normalizing Flows (NF) are powerful likelihood-based generative models that are able to trade off between expressivity and tractability to model complex densities. A now well estab…
Preventing Manifold Intrusion with Locality: Local Mixup
Raphael Baena, Lucas Drumetz, Vincent Gripon
Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs. It has been shown to improve accuracy when used to…
Graphs as Tools to Improve Deep Learning Methods
Carlos Lassance, Myriam Bontonou, Mounia Hamidouche +3
In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still…
Learning stochastic dynamical systems with neural networks mimicking the Euler-Maruyama scheme
Noura Dridi, Lucas Drumetz, Ronan Fablet
Stochastic differential equations (SDEs) are one of the most important representations of dynamical systems. They are notable for the ability to include a deterministic component o…
Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations
Duong Nguyen, Said Ouala, Lucas Drumetz +1
The data-driven recovery of the unknown governing equations of dynamical systems has recently received an increasing interest. However, the identification of governing equations re…
Joint learning of variational representations and solvers for inverse problems with partially-observed data
Ronan Fablet, Lucas Drumetz, Francois Rousseau
Designing appropriate variational regularization schemes is a crucial part of solving inverse problems, making them better-posed and guaranteeing that the solution of the associate…
EM-like Learning Chaotic Dynamics from Noisy and Partial Observations
Duong Nguyen, Said Ouala, Lucas Drumetz +1
The identification of the governing equations of chaotic dynamical systems from data has recently emerged as a hot topic. While the seminal work by Brunton et al. reported proof-of…