 |
Jean Feydy CR Inria |
email: first name dot last name at inria dot fr postal address: Paris SantéCampus, 10 rue d’Oradour sur Glane, 75015 Paris web page: www.jeanfeydy.com bio: Jean Feydy joined the HeKA team in 2021 after a PhD with Alain Trouvé (ENS Paris-Saclay) and a post-doc with Michael Bronstein (Imperial College London). His main research interests lay at the intersection between geometry, machine learning and high-performance computing with a strong expertise in shape analysis, optimal transport theory and GPU programming. Jean develops the KeOps and GeomLoss libraries, two software packages that open new doors for geometric data analysis, beyond convolutions. He is now working on turning these mathematical tools into genuine clinical methods, with a focus on computational anatomy and pharmaco-vigilance. |
Research projects
See my personal webpage.
Publications
See my personal webpage for up-to-date information and additional resources.
2024
Preprints, Working Papers, …
- ref_biblio
- Thibault Séjourné, Jean Feydy, François-Xavier Vialard, Alain Trouvé, Gabriel Peyré. Sinkhorn Divergences for Unbalanced Optimal Transport. 2024. ⟨hal-04435912⟩
- Accès au bibtex
-
2023
Journal articles
- ref_biblio
- Tom Boeken, Jean Feydy, Augustin Lecler, Philippe Soyer, Antoine Feydy, et al.. Artificial intelligence in diagnostic and interventional radiology: Where are we now?. Diagnostic and Interventional Imaging, 2023, 104 (1), pp.1-5. ⟨10.1016/j.diii.2022.11.004⟩. ⟨hal-03949288⟩
- Accès au bibtex
-
Conference papers
- ref_biblio
- Freyr Sverrisson, Mehmet Akdel, Dylan Abramson, Jean Feydy, Alexander Goncearenco, et al.. DiffMaSIF: Surface-based Protein-Protein Docking with Diffusion Models. Machine Learning in Structural Biology workshop at NeurIPS 2023, Dec 2023, New Orleans, United States. ⟨hal-04360638⟩
- Accès au texte intégral et bibtex
-
2022
Journal articles
- ref_biblio
- Maxime Lacroix, Theodore Aouad, Jean Feydy, David Biau, Frédérique Larousserie, et al.. Artificial intelligence in musculoskeletal oncology imaging: A critical review of current applications. Diagnostic and Interventional Imaging, 2022, ⟨10.1016/j.diii.2022.10.004⟩. ⟨hal-03909429⟩
- Accès au bibtex
-
Conference papers
- ref_biblio
- Freyr Sverrisson, Jean Feydy, Joshua Southern, Michael M Bronstein, Bruno E Correia. Physics-informed deep neural network for rigid-body protein docking. MLDD 2022 – Machine Learning for Drug Discovery Workshop of ICLR 2022, Apr 2022, Virtual conference, France. ⟨hal-03949198⟩
- Accès au texte intégral et bibtex
-
Book sections
- ref_biblio
- Pierre Sabatier, Jean Feydy, Anne-Sophie Jannot. Accelerating High-Dimensional Temporal Modelling Using Graphics Processing Units for Pharmacovigilance Signal Detection on Real-Life Data. Challenges of Trustable AI and Added-Value on Health, IOS Press, 2022, Studies in Health Technology and Informatics, ⟨10.3233/SHTI220401⟩. ⟨hal-03911970⟩
- Accès au bibtex
-
2021
Journal articles
- ref_biblio
- Benjamin Charlier, Jean Feydy, Joan Glaunès, François-David Collin, Ghislain Durif. Kernel Operations on the GPU, with Autodiff,without Memory Overflows. Journal of Machine Learning Research, 2021, 22 (74), pp.1-6. ⟨hal-02517462v2⟩
- Accès au texte intégral et bibtex
-
Conference papers
- ref_biblio
- Zhengyang Shen, Jean Feydy, Peirong Liu, Ariel Hernán Curiale, Ruben San Jose Estepar, et al.. Accurate Point Cloud Registration with Robust Optimal Transport. NeurIPS 2021, Dec 2021, Virtual conference, France. ⟨hal-03949118⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Freyr Sverrisson, Jean Feydy, Bruno E Correia, Michael M Bronstein. Fast end-to-end learning on protein surfaces. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2021, Nashville, France. pp.15267-15276, ⟨10.1109/CVPR46437.2021.01502⟩. ⟨hal-03947242⟩
- Accès au texte intégral et bibtex
-
2020
Conference papers
- ref_biblio
- Jean Feydy, Joan Alexis Glaunès, Benjamin Charlier, Michael M Bronstein. Fast geometric learning with symbolic matrices. Thirty-fourth Conference on Neural Information Processing Systems, Dec 2020, Virtual-only, Canada. ⟨hal-03232595⟩
- Accès au texte intégral et bibtex
-
Theses
- ref_biblio
- Jean Feydy. Analyse de données géométriques, au delà des convolutions. Mathématiques générales [math.GM]. Université Paris-Saclay, 2020. Français. ⟨NNT : 2020UPASN017⟩. ⟨tel-02945979⟩
- Accès au texte intégral et bibtex
-
2019
Conference papers
- ref_biblio
- Jean Feydy, Pierre Roussillon, Alain Trouvé, Pietro Gori. Fast and Scalable Optimal Transport for Brain Tractograms. MICCAI 2019, Oct 2019, Shenzhen, China. ⟨10.1007/978-3-030-32248-9_71⟩. ⟨hal-02264177⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Jean Feydy, Thibault Séjourné, François-Xavier Vialard, Shun-Ichi Amari, Alain Trouvé, et al.. Interpolating between Optimal Transport and MMD using Sinkhorn Divergences. AISTATS, Apr 2019, Naha, Okinawa, Japan. pp.2681-2690, ⟨10.48550/arXiv.1810.08278⟩. ⟨hal-04435902⟩
- Accès au bibtex
-
2018
Conference papers
- ref_biblio
- Benjamin Charlier, Jean Feydy, Joan Alexis Glaunès. KeOps: Calcul rapide sur GPU dans les espaces à noyaux. Journées de Statistique de la SFdS, May 2018, Palaiseau, France. ⟨hal-03973487⟩
- Accès au bibtex
-
Preprints, Working Papers, …
- ref_biblio
- Jean Feydy, Thibault Séjourné, François-Xavier Vialard, Shun-Ichi Amari, Alain Trouvé, et al.. Interpolating between Optimal Transport and MMD using Sinkhorn Divergences. 2018. ⟨hal-01898858⟩
- Accès au texte intégral et bibtex
-
- ref_biblio
- Jean Feydy, Alain Trouvé. Global divergences between measures: from Hausdorff distance to Optimal Transport. 2018. ⟨hal-01827184v2⟩
- Accès au texte intégral et bibtex
-
2017
Conference papers
- ref_biblio
- Jean Feydy, Benjamin Charlier, François-Xavier Vialard, Gabriel Peyré. Optimal Transport for Diffeomorphic Registration. MICCAI 2017, Sep 2017, Quebec, Canada. ⟨hal-01540455⟩
- Accès au texte intégral et bibtex
-
