ML

Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds
While many Machine Learning methods were developed or transposed on Riemannian manifolds to tackle data with known non Euclidean …
Clément Bonet, Lucas Drumetz, Nicolas Courty
Cite Preprint
Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds
SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
Many approaches in machine learning rely on a weighted graph to encode the similarities between samples in a dataset. Entropic …
Hugues Van Assel, Titouan Vayer, Rémi Flamary, Nicolas Courty
Cite URL NeurIPS 2023
SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
When dealing with electro or magnetoencephalography records, many supervised prediction tasks are solved by working with covariance …
Clément Bonet, Benoît Malézieux, Alain Rakotomamonjy, Lucas Drumetz, Thomas Moreau, Matthieu Kowalski, Nicolas Courty
Cite DOI URL ICML 2023
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
Unbalanced CO-Optimal Transport
Optimal transport (OT) compares probability distributions by computing a meaningful alignment between their samples. CO-optimal …
Quang Huy Tran, Hicham Janati, Nicolas Courty, Rémi Flamary, Ievgen Redko, Pinar Demetci, Ritambhara Singh
Cite DOI URL AAAI 2023
Unbalanced CO-Optimal Transport