Time series representations with hard-coded invariances
Abstract
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Duis posuere tellus ac convallis placerat. Proin tincidunt magna sed ex sollicitudin condimentum. Sed ac faucibus dolor, scelerisque sollicitudin nisi. Cras purus urna, suscipit quis sapien eu, pulvinar tempor diam. Quisque risus orci, mollis id ante sit amet, gravida egestas nisl. Sed ac tempus magna. Proin in dui enim. Donec condimentum, sem id dapibus fringilla, tellus enim condimentum arcu, nec volutpat est felis vel metus. Vestibulum sit amet erat at nulla eleifend gravida.
Type
Publication
Forty-second International Conference on Machine Learning
Status
Peer-reviewed
Open access
Funding
National Science Foundation (NSF-2401234)
European Research Council (ERC-StG-101234)
Authors
Thibaut Germain
(he/him)
Postdoctoral Researcher
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.