Hugo Lebeau
Ph.D. start: October 2021 Expected end: October 2024 Remaining time:
Academic Background
- Master MVA with honors of the jury Mathematics, Machine Learning, Computer Vision
- ENSTA Paris ranked top 5% Applied Mathematics, Optimization and Data Science
Research topics
High-Dimensional Statistics Random Matrix Theory Random Tensors
- Low-Rank Tensor Approximations Analysis of spiked tensor models with random matrix tools.
- Random Tensors and Clustering Theoretical study of complex clustering tasks (multi-view clustering, time-varying clusters).
- Data Stream Clustering Kernel spectral clustering under limited memory constraints.
Publications
- Submitted to JMLR – A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation, Hugo Lebeau, Florent Chatelain, Romain Couillet [preprint]
- IEEE Signal Processing Letters – Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering, Hugo Lebeau, Florent Chatelain, Romain Couillet [article][code]
- ICLR 2024 – Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model, Hugo Lebeau, Mohamed El Amine Seddik, José Henrique De Morais Goulart [article][code]
- GRETSI 2023 – HOSVD Tronquée : Analyse d'une Approximation Tensorielle Rapide, Hugo Lebeau, Romain Couillet, Florent Chatelain [article]
- GRETSI 2022 – Une analyse par matrices aléatoires du clustering en ligne : comprendre l’impact des limitations en mémoire, Hugo Lebeau, Romain Couillet, Florent Chatelain [article]
- ICML 2022 – A Random Matrix Analysis of Data Stream Clustering: Coping With Limited Memory Resources, Hugo Lebeau, Romain Couillet, Florent Chatelain [article][code][video]
Teaching
During my PhD, I take part in several courses as teaching assistant. I am also following a curriculum of trainings on teaching for higher education.
I have written (in French) a short reflection on my first two years of teaching. It is available here.
