Hugues Van Assel
Postdoctoral Fellow at Genentech, South San Francisco CA

I am a postdoc at Genentech with Aviv Regev and Tommaso Biancalani.
My primary interests are in representation learning, self-supervised learning and dimensionality reduction. I develop computational methods that leverage optimal transport and probabilistic modeling to compute meaningful and robust data representations suitable for real-world applications, typically in life sciences.
I am a strong advocate for open and accessible science through projects such as:
- TorchDR : a modular, GPU-friendly toolbox for dimensionality reduction (DR) that offers a unified interface for state-of-the-art DR methods.
- stable-ssl : a library offering essential boilerplate code for a wide range of self-supervised learning tasks.
I did my PhD in the math department of ENS Lyon working on Optimal Transport and Probabilistic Modeling for Dimensionality Reduction (the manuscript is available here). Prior to my PhD, I was a student at Ecole polytechnique and MVA.
Publications
-
A Graph Matching Approach to Balanced Data Sub-Sampling for Self-Supervised Learning
Hugues Van Assel, Randall Balestriero
NeurIPS 2024, Self-Supervised Learning Workshop
PDF (workshop), Poster (workshop) -
Distributional Reduction: Unifying Dimensionality Reduction and Clustering with Gromov-Wasserstein
Hugues Van Assel, Cédric Vincent-Cuaz, Nicolas Courty, Rémi Flamary, Pascal Frossard, Titouan Vayer
NeurIPS 2023, Optimal Transport for Machine Learning Workshop
PDF (long version), PDF (workshop), Poster (workshop) -
Optimal Transport with Adaptive Regularisation
Hugues Van Assel, Titouan Vayer, Rémi Flamary, Nicolas Courty
NeurIPS 2023, Optimal Transport for Machine Learning Workshop
PDF, Poster -
SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
Hugues Van Assel, Titouan Vayer, Rémi Flamary, Nicolas Courty
NeurIPS 2023
PDF, Poster -
A Probabilistic Graph Coupling View of Dimension Reduction
Hugues Van Assel, Thibault Espinasse, Julien Chiquet, Franck Picard
NeurIPS 2022
PDF, Poster