Variational Flow Models: Flowing in Your Style
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913456848896000 |
|---|---|
| author | Do, Kien Kieu, Duc Nguyen, Toan Nguyen, Dang Le, Hung Nguyen, Dung Nguyen, Thin |
| author_facet | Do, Kien Kieu, Duc Nguyen, Toan Nguyen, Dang Le, Hung Nguyen, Dung Nguyen, Thin |
| contents | We propose a systematic training-free method to transform the probability flow of a "linear" stochastic process characterized by the equation X_{t}=a_{t}X_{0}+σ_{t}X_{1} into a straight constant-speed (SC) flow, reminiscent of Rectified Flow. This transformation facilitates fast sampling along the original probability flow via the Euler method without training a new model of the SC flow. The flexibility of our approach allows us to extend our transformation to inter-convert two posterior flows of two distinct linear stochastic processes. Moreover, we can easily integrate high-order numerical solvers into the transformed SC flow, further enhancing the sampling accuracy and efficiency. Rigorous theoretical analysis and extensive experimental results substantiate the advantages of our framework. Our code is available at this [https://github.com/clarken92/VFM||link]. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02977 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Variational Flow Models: Flowing in Your Style Do, Kien Kieu, Duc Nguyen, Toan Nguyen, Dang Le, Hung Nguyen, Dung Nguyen, Thin Machine Learning Artificial Intelligence We propose a systematic training-free method to transform the probability flow of a "linear" stochastic process characterized by the equation X_{t}=a_{t}X_{0}+σ_{t}X_{1} into a straight constant-speed (SC) flow, reminiscent of Rectified Flow. This transformation facilitates fast sampling along the original probability flow via the Euler method without training a new model of the SC flow. The flexibility of our approach allows us to extend our transformation to inter-convert two posterior flows of two distinct linear stochastic processes. Moreover, we can easily integrate high-order numerical solvers into the transformed SC flow, further enhancing the sampling accuracy and efficiency. Rigorous theoretical analysis and extensive experimental results substantiate the advantages of our framework. Our code is available at this [https://github.com/clarken92/VFM||link]. |
| title | Variational Flow Models: Flowing in Your Style |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.02977 |