Splitting Regularized Wasserstein Proximal Algorithms for Nonsmooth Sampling Problems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918088455225344 |
|---|---|
| author | Han, Fuqun Osher, Stanley Li, Wuchen |
| author_facet | Han, Fuqun Osher, Stanley Li, Wuchen |
| contents | Sampling from nonsmooth target probability distributions is essential in various applications, including the Bayesian Lasso. We propose a splitting-based sampling algorithm for the time-implicit discretization of the probability flow for the Fokker-Planck equation, where the score function, defined as the gradient logarithm of the current probability density function, is approximated by the regularized Wasserstein proximal. When the prior distribution is the Laplace prior, our algorithm is explicitly formulated as a deterministic interacting particle system, incorporating softmax operators and shrinkage operations to efficiently compute the gradient drift vector field and the score function. We verify the convergence towards target distributions regarding Rényi divergences and Wasserstein-2 distance under suitable conditions. Numerical experiments in high-dimensional nonsmooth sampling problems, such as sampling from mixed Gaussian and Laplace distributions, logistic regressions, image restoration with $L_1$-TV regularization, and Bayesian neural networks, demonstrate the efficiency and robust performance of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16773 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Splitting Regularized Wasserstein Proximal Algorithms for Nonsmooth Sampling Problems Han, Fuqun Osher, Stanley Li, Wuchen Computation Sampling from nonsmooth target probability distributions is essential in various applications, including the Bayesian Lasso. We propose a splitting-based sampling algorithm for the time-implicit discretization of the probability flow for the Fokker-Planck equation, where the score function, defined as the gradient logarithm of the current probability density function, is approximated by the regularized Wasserstein proximal. When the prior distribution is the Laplace prior, our algorithm is explicitly formulated as a deterministic interacting particle system, incorporating softmax operators and shrinkage operations to efficiently compute the gradient drift vector field and the score function. We verify the convergence towards target distributions regarding Rényi divergences and Wasserstein-2 distance under suitable conditions. Numerical experiments in high-dimensional nonsmooth sampling problems, such as sampling from mixed Gaussian and Laplace distributions, logistic regressions, image restoration with $L_1$-TV regularization, and Bayesian neural networks, demonstrate the efficiency and robust performance of the proposed method. |
| title | Splitting Regularized Wasserstein Proximal Algorithms for Nonsmooth Sampling Problems |
| topic | Computation |
| url | https://arxiv.org/abs/2502.16773 |