paper-with-me

홈 › Papers

GeONet: a neural operator for learning the Wasserstein geodesic

2022-09-28 · Andrew Gracyk, Xiaohui Chen

Optimal transport (OT) offers a versatile framework to compare complex data distributions in a geometrically meaningful way. Traditional methods for computing the Wasserstein distance and geodesic between probability measures require mesh-specific domain discretization and suffer from the curse-of-dimensionality. We present GeONet, a mesh-invariant deep neural operator network that learns the non-linear mapping from the input pair of initial and terminal distributions to the Wasserstein geodesic connecting the two endpoint distributions. In the offline training stage, GeONet learns the saddle point optimality conditions for the dynamic formulation of the OT problem in the primal and dual spaces that are characterized by a coupled PDE system. The subsequent inference stage is instantaneous and can be deployed for real-time predictions in the online learning setting. We demonstrate that GeONet achieves comparable testing accuracy to the standard OT solvers on simulation examples and the MNIST dataset with considerably reduced inference-stage computational cost by orders of magnitude.

📄 PDF Abstract BibTeX arXiv:2209.14440

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GeoNet: Deep Geodesic Networks for Point Cloud Analysis

2019-01-03 · CVPR 2019 6 · Tong He, Haibin Huang, Li Yi, Yuqian Zhou 외

Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling. However, such connectivity information is lost in point clouds. Thus we introduce GeoNet, the first deep learning …

General Classification

Another Look at Log-PCA for Probability Measures: A Dynamical Formulation and Statistical Convergence

2026-06-15 · Peng Xu, Changbo Zhu, Young-Heon Kim, Xiaohui Chen arxiv

This paper is concerned with learning principal variations of random probability measures on $\mathbb{R}^m$ under the Wasserstein geometry. We introduce a new dynamical formulation to interpret the log-PCA, a linearized …

Learning High Dimensional Wasserstein Geodesics

2021-02-05 · Shu Liu, Shaojun Ma, Yongxin Chen, Hongyuan Zha 외

We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions. By applying the method of Lagrange multipliers to the dynamic formulatio…

Vocal Bursts Intensity Prediction

Wasserstein Geodesic Generator for Conditional Distributions

2023-08-20 · Young-geun Kim, Kyungbok Lee, Youngwon Choi, Joong-Ho Won 외

Generating samples given a specific label requires estimating conditional distributions. We derive a tractable upper bound of the Wasserstein distance between conditional distributions to lay the theoretical groundwork t…

On the Wasserstein Geodesic Principal Component Analysis of probability measures

2025-06-04 · Nina Vesseron, Elsa Cazelles, Alice Le Brigant, Thierry Klein

This paper focuses on Geodesic Principal Component Analysis (GPCA) on a collection of probability distributions using the Otto-Wasserstein geometry. The goal is to identify geodesic curves in the space of probability mea…