Fast Sinkhorn I: An O (N) algorithm for the Wasserstein-1 metric

Q Liao, J Chen, Z Wang, B Bai, S Jin, H Wu - arXiv preprint arXiv …, 2022 - arxiv.org
The Wasserstein metric is broadly used in optimal transport for comparing two probabilistic
distributions, with successful applications in various fields such as machine learning, signal …

Fast Sinkhorn II: Collinear triangular matrix and linear time accurate computation of optimal transport

Q Liao, Z Wang, J Chen, B Bai, S Jin, H Wu - Journal of Scientific …, 2024 - Springer
In our previous work (Liao et al. in Commun Math Sci, 2022), the complexity of Sinkhorn
iteration is reduced from O (N 2) to the optimal O (N) by leveraging the special structure of …

An Unsupervised Deep Learning Approach for the Wave Equation Inverse Problem

XB Yan, K Wu, ZQJ Xu, Z Ma - arXiv preprint arXiv:2311.04531, 2023 - arxiv.org
Full-waveform inversion (FWI) is a powerful geophysical imaging technique that infers high-
resolution subsurface physical parameters by solving a non-convex optimization problem …

A numerical algorithm with linear complexity for Multi-marginal Optimal Transport with Cost

C Chen, J Chen, B Luo, S Jin, H Wu - arXiv preprint arXiv:2405.19246, 2024 - arxiv.org
Numerically solving multi-marginal optimal transport (MMOT) problems is computationally
prohibitive, even for moderate-scale instances involving $ l\ge4 $ marginals with support …

[图书][B] Computational Inversion with Wasserstein Distances and Neural Network Induced Loss Functions

W Ding - 2022 - search.proquest.com
This thesis presents a systematic computational investigation of loss functions in solving
inverse problems of partial differential equations. The primary efforts are spent on …