Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.06702 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915659445698560 |
|---|---|
| author | Meng, Xiangjun Wang, Zhongjian |
| author_facet | Meng, Xiangjun Wang, Zhongjian |
| contents | We provide attainable analytical tools to estimate the error of flow-based generative models under the Wasserstein metric and to establish the optimal sampling iteration complexity bound with respect to dimension as $O(\sqrt{d})$. We show this error can be explicitly controlled by two parts: the Lipschitzness of the push-forward maps of the backward flow which scales independently of the dimension; and a local discretization error scales $O(\sqrt{d})$ in terms of dimension. The former one is related to the existence of Lipschitz changes of variables induced by the (heat) flow. The latter one consists of the regularity of the score function in both spatial and temporal directions.
These assumptions are valid in the flow-based generative model associated with the Föllmer process and $1$-rectified flow under the Gaussian tail assumption. As a consequence, we show that the sampling iteration complexity grows linearly with the square root of the trace of the covariance operator, which is related to the invariant distribution of the forward process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pathway to $O(\sqrt{d})$ Complexity bound under Wasserstein metric of flow-based models Meng, Xiangjun Wang, Zhongjian Machine Learning We provide attainable analytical tools to estimate the error of flow-based generative models under the Wasserstein metric and to establish the optimal sampling iteration complexity bound with respect to dimension as $O(\sqrt{d})$. We show this error can be explicitly controlled by two parts: the Lipschitzness of the push-forward maps of the backward flow which scales independently of the dimension; and a local discretization error scales $O(\sqrt{d})$ in terms of dimension. The former one is related to the existence of Lipschitz changes of variables induced by the (heat) flow. The latter one consists of the regularity of the score function in both spatial and temporal directions. These assumptions are valid in the flow-based generative model associated with the Föllmer process and $1$-rectified flow under the Gaussian tail assumption. As a consequence, we show that the sampling iteration complexity grows linearly with the square root of the trace of the covariance operator, which is related to the invariant distribution of the forward process. |
| title | Pathway to $O(\sqrt{d})$ Complexity bound under Wasserstein metric of flow-based models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.06702 |