On the Convergence of Wasserstein Gradient Descent for Sampling
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912872176549888 |
|---|---|
| author | Ta, Van Chien Chu, Thi Mai Hong Tran, Minh-Ngoc |
| author_facet | Ta, Van Chien Chu, Thi Mai Hong Tran, Minh-Ngoc |
| contents | This paper studies the optimization of the KL functional on the Wasserstein space of probability measures, and develops a sampling framework based on Wasserstein gradient descent (WGD). We identify two important subclasses of the Wasserstein space for which the WGD scheme is guaranteed to converge, thereby providing new theoretical foundations for optimization-based sampling methods on measure spaces. For practical implementation, we construct a particle-based WGD algorithm in which the score function is estimated via score matching. Through a series of numerical experiments, we demonstrate that WGD can provide good approximation to a variety of complex target distributions, including those that pose substantial challenges for standard MCMC and parametric variational Bayes methods. These results suggest that WGD offers a promising and flexible alternative for scalable Bayesian inference in high-dimensional or multimodal settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03413 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Convergence of Wasserstein Gradient Descent for Sampling Ta, Van Chien Chu, Thi Mai Hong Tran, Minh-Ngoc Computation This paper studies the optimization of the KL functional on the Wasserstein space of probability measures, and develops a sampling framework based on Wasserstein gradient descent (WGD). We identify two important subclasses of the Wasserstein space for which the WGD scheme is guaranteed to converge, thereby providing new theoretical foundations for optimization-based sampling methods on measure spaces. For practical implementation, we construct a particle-based WGD algorithm in which the score function is estimated via score matching. Through a series of numerical experiments, we demonstrate that WGD can provide good approximation to a variety of complex target distributions, including those that pose substantial challenges for standard MCMC and parametric variational Bayes methods. These results suggest that WGD offers a promising and flexible alternative for scalable Bayesian inference in high-dimensional or multimodal settings. |
| title | On the Convergence of Wasserstein Gradient Descent for Sampling |
| topic | Computation |
| url | https://arxiv.org/abs/2602.03413 |