Consistency Training with Physical Constraints
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909488157556736 |
|---|---|
| author | Chang, Che-Chia Dai, Chen-Yang Lin, Te-Sheng Lai, Ming-Chih Lai, Chieh-Hsin |
| author_facet | Chang, Che-Chia Dai, Chen-Yang Lin, Te-Sheng Lai, Ming-Chih Lai, Chieh-Hsin |
| contents | We propose a physics-aware Consistency Training (CT) method that accelerates sampling in Diffusion Models with physical constraints. Our approach leverages a two-stage strategy: (1) learning the noise-to-data mapping via CT, and (2) incorporating physics constraints as a regularizer. Experiments on toy examples show that our method generates samples in a single step while adhering to the imposed constraints. This approach has the potential to efficiently solve partial differential equations (PDEs) using deep generative modeling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07636 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Consistency Training with Physical Constraints Chang, Che-Chia Dai, Chen-Yang Lin, Te-Sheng Lai, Ming-Chih Lai, Chieh-Hsin Machine Learning We propose a physics-aware Consistency Training (CT) method that accelerates sampling in Diffusion Models with physical constraints. Our approach leverages a two-stage strategy: (1) learning the noise-to-data mapping via CT, and (2) incorporating physics constraints as a regularizer. Experiments on toy examples show that our method generates samples in a single step while adhering to the imposed constraints. This approach has the potential to efficiently solve partial differential equations (PDEs) using deep generative modeling. |
| title | Consistency Training with Physical Constraints |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.07636 |