Publications

Riemannian adversarial attacks on Symmetric Positive Definite matrices

Dimitri Timoz, Thibault de Surrel and Florian Yger
Published in ICASSP 2026, 2026
Download paper | HAL

SPDNet-AE: a Compact SPD Representation through Riemannian Autoencoding

Charlotte Boucherie, Thibault de Surrel and Florian Yger
Published in ESANN 2026, 2026
Download paper | HAL

A probabilistic view on Riemannian machine learning models for SPD matrices

Thibault de Surrel, Florian Yger, Fabien Lotte, and Sylvain Chevallier
Published in Geometric Science on Information (GSI), 2025
Download paper | HAL

Interpretability of Riemannian tools used in Brain Computer Interfaces

Thibault de Surrel, Tristan Venot, Marie-Constance Corsi, Florian Yger
Published in IEEE Machine Learning For Signal Processing (MLSP), 2025
Download paper | HAL

Wrapped Gaussian on the manifold of Symmetric Positive Definite Matrices

Thibault de Surrel, Fabien Lotte, Sylvain Chevallier and Florian Yger
Published in International Conference on Machine Learning (ICML), 2025
Download paper | HAL

Geometry-Aware visualization of high dimensional Symmetric Positive Definite matrices

Thibault de Surrel, Sylvain Chevallier, Fabien Lotte and Florian Yger
Published in Transactions on Machine Learning Research, 2025
Download paper | HAL

Averaging trajectories on the manifold of symmetric positive definite matrices

Thibault de Surrel, Florian Yger, Sylvain Chevallier and Fabien Lotte
Published in EUSIPCO, 2024
Download paper | HAL

RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds

Thibault de Surrel, Felix Hensel, Mathieu Carrière, Théo Lacombe, Yuichi Ike, Hiroaki Kurihara, Marc Glisse and Frédéric Chazal
Published in Proceedings of Topological, Algebraic, and Geometric Learning Workshops, 2022
Download paper | HAL | arXiv

Thibault de Surrel

Publications

Preprints