Thibaut Germain

Thibaut Germain

(he/him)

Postdoctoral Researcher

CMAP - Ecole Polytechnique

About me

My research combines machine learning and signal processing with geometric methods to study time series and dynamical systems.

Since March 2025, I have been a postdoctoral researcher at CMAP - Ecole Polytechnique, working with Karim Lounici and Rémi Flamary. My work combines operator learning and optimal transport to compare dynamical systems, uncover shared dynamical structure, and transfer knowledge across systems.

Previously, I completed my PhD at Centre Borelli, under the supervision of Charles Truong and Laurent Oudre. I developed methods tailored for the discovery and statistical analysis of time series patterns with a particular focus on biomedical applications.

News

Recent Publications
A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems. ICLR.
Discovering Multiple Subdimensional Motifs in Multivariate Time Series. EUSIPCO.
Geometric Dictionary Learning of Dynamical Systems with Optimal Transport. arXiv.
An α7 nicotinic and GABA_B receptor-mediated pathway controls acetylcholine release in the tripartite neuromuscular junction. J Physiol.
Time series motif discovery: a comprehensive evaluation. PVLDB.