Search Results for author: Jean Feydy

Found 7 papers, 4 papers with code

Accurate Point Cloud Registration with Robust Optimal Transport

2 code implementations NeurIPS 2021 Zhengyang Shen, Jean Feydy, Peirong Liu, Ariel Hernán Curiale, Ruben San Jose Estepar, Raul San Jose Estepar, Marc Niethammer

Finally, we showcase the performance of transport-enhanced registration models on a wide range of challenging tasks: rigid registration for partial shapes; scene flow estimation on the Kitti dataset; and nonparametric registration of lung vascular trees between inspiration and expiration.

Point Cloud Registration Scene Flow Estimation

Fast and Scalable Optimal Transport for Brain Tractograms

no code implementations5 Jul 2021 Jean Feydy, Pierre Roussillon, Alain Trouvé, Pietro Gori

The parameters -- blur and reach -- of our method are meaningful, defining the minimum and maximum distance at which two fibers are compared with each other.

Fast End-to-End Learning on Protein Surfaces

1 code implementation CVPR 2021 Freyr Sverrisson, Jean Feydy, Bruno E. Correia, Michael M. Bronstein

These results will considerably ease the deployment of deep learning methods in protein science and open the door for end-to-end differentiable approaches in protein modeling tasks such as function prediction and design.

Fast geometric learning with symbolic matrices

no code implementations NeurIPS 2020 Jean Feydy, Joan Glaunès, Benjamin Charlier, Michael Bronstein

Geometric methods rely on tensors that can be encoded using a symbolic formula and data arrays, such as kernel and distance matrices.

Kernel Operations on the GPU, with Autodiff, without Memory Overflows

no code implementations27 Mar 2020 Benjamin Charlier, Jean Feydy, Joan Alexis Glaunès, François-David Collin, Ghislain Durif

The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices.

Sinkhorn Divergences for Unbalanced Optimal Transport

4 code implementations28 Oct 2019 Thibault Séjourné, Jean Feydy, François-Xavier Vialard, Alain Trouvé, Gabriel Peyré

Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems.

Interpolating between Optimal Transport and MMD using Sinkhorn Divergences

1 code implementation18 Oct 2018 Jean Feydy, Thibault Séjourné, François-Xavier Vialard, Shun-ichi Amari, Alain Trouvé, Gabriel Peyré

Comparing probability distributions is a fundamental problem in data sciences.

Statistics Theory Statistics Theory 62

Cannot find the paper you are looking for? You can Submit a new open access paper.