Hugues Van Assel

photo_profil.jpeg

hugues.van_assel@ens-lyon.fr

I am a PhD student in the department of Mathematics (UMPA) of Ecole Normale Supérieure de Lyon supervised by Aurélien Garivier and Titouan Vayer and in collaboration with Rémi Flamary and Nicolas Courty.

I work in the field of machine learning / data analysis. In my research, I develop unsupervised learning algorithms based on optimal transport and probabilistic modelling. I focus mainly on dimensionality reduction and clustering. I am particularly interested in biological applications (cellular biology, neuroscience …) of these methods.

Before starting my PhD, I was a student at Ecole polytechnique and MVA master. More informations can be found in my CV.

news

Feb 12, 2024 New preprint out! Exciting work relating dimensionality reduction and clustering methods to the Gromov-Wasserstein OT problem.
Dec 10, 2023 I will be at NeurIPS 2023 to present SNEkhorn as well as two posters at the OTML workshop.
Jun 30, 2023 Had an exciting week at the Generative Modelling Summer School. Thanks a lot to the organizers!
Sep 22, 2022 The first paper of my PhD : A Probabilistic Graph Coupling View of Dimension Reduction made it to NeurIPS 2022!

selected publications

  1. Preprint
    Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein Projection
    Hugues Van Assel, Cédric Vincent-Cuaz, Nicolas Courty, Rémi Flamary, Pascal Frossard, and Titouan Vayer
    Preprint, 2024
    PDF
  2. NeurIPS
    SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
    Hugues Van Assel, Titouan Vayer, Rémi Flamary, and Nicolas Courty
    Advances in Neural Information Processing Systems, 2023
    PDF Poster
  3. NeurIPS
    A Probabilistic Graph Coupling View of Dimension Reduction
    Hugues Van Assel, Thibault Espinasse, Julien Chiquet, and Franck Picard
    Advances in Neural Information Processing Systems, 2022
    PDF Poster