Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2503.10219 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910873846546432 |
|---|---|
| author | Na, Kunwoo Lee, Junghyun Yun, Se-Young Lim, Sungbin |
| author_facet | Na, Kunwoo Lee, Junghyun Yun, Se-Young Lim, Sungbin |
| contents | Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Probability-Flow ODE in Infinite-Dimensional Function Spaces Na, Kunwoo Lee, Junghyun Yun, Se-Young Lim, Sungbin Machine Learning Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs. |
| title | Probability-Flow ODE in Infinite-Dimensional Function Spaces |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.10219 |