Two-Step Diffusion: Fast Sampling and Reliable Prediction for 3D Keller--Segel and KPP Equations in Fluid Flows
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_ | 1866917226916872192 |
|---|---|
| author | Shen, Zhenda Wang, Zhongjian Xin, Jack Zhang, Zhiwen |
| author_facet | Shen, Zhenda Wang, Zhongjian Xin, Jack Zhang, Zhiwen |
| contents | We study fast and reliable generative transport for the 3D KS (Keller-Segel) and KPP (Kolmogorov-Petrovsky-Piskunov) equations in the presence of fluid flows with the goal to approximate the map between initial and terminal distributions for a range of physical parameters $σ$ under the Wasserstein metric. To minimize the inaccuracy of direct Wasserstein solver, we propose a two-stage pipeline that retains one-step efficiency while reinstating an explicit $W_2$ objective where it is tractable. In Stage I, a Meanflow-style regressor yields a deterministic, one-step global transport that moves particles close to their terminal states. In Stage II, we freeze this initializer and train a near-identity corrector (Deep Particle, DP) that directly minimizes a mini-batch $W_2$ objective using warm-started optimal transport couplings computed on the Meanflow outputs. Crucially, after the one-step transport (from Stage I) concentrating mass on the approximated correct support, the induced geometry stabilizes high-dimensional $W_2$ computation of the direct Wasserstein solver. We validate our construction in the 3D KS and KPP equations subject to fluid flows with ordered and chaotic streamlines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20024 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Two-Step Diffusion: Fast Sampling and Reliable Prediction for 3D Keller--Segel and KPP Equations in Fluid Flows Shen, Zhenda Wang, Zhongjian Xin, Jack Zhang, Zhiwen Computational Physics Fluid Dynamics 65M75, 65C35, 35Q92 We study fast and reliable generative transport for the 3D KS (Keller-Segel) and KPP (Kolmogorov-Petrovsky-Piskunov) equations in the presence of fluid flows with the goal to approximate the map between initial and terminal distributions for a range of physical parameters $σ$ under the Wasserstein metric. To minimize the inaccuracy of direct Wasserstein solver, we propose a two-stage pipeline that retains one-step efficiency while reinstating an explicit $W_2$ objective where it is tractable. In Stage I, a Meanflow-style regressor yields a deterministic, one-step global transport that moves particles close to their terminal states. In Stage II, we freeze this initializer and train a near-identity corrector (Deep Particle, DP) that directly minimizes a mini-batch $W_2$ objective using warm-started optimal transport couplings computed on the Meanflow outputs. Crucially, after the one-step transport (from Stage I) concentrating mass on the approximated correct support, the induced geometry stabilizes high-dimensional $W_2$ computation of the direct Wasserstein solver. We validate our construction in the 3D KS and KPP equations subject to fluid flows with ordered and chaotic streamlines. |
| title | Two-Step Diffusion: Fast Sampling and Reliable Prediction for 3D Keller--Segel and KPP Equations in Fluid Flows |
| topic | Computational Physics Fluid Dynamics 65M75, 65C35, 35Q92 |
| url | https://arxiv.org/abs/2601.20024 |