Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2505.23264 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910973685661696 |
|---|---|
| author | Wang, Fangyikang Yin, Hubery Zhuang, Shaobin Zhu, Huminhao Li, Yinan Qian, Lei Zhang, Chao Zhao, Hanbin Qian, Hui Li, Chen |
| author_facet | Wang, Fangyikang Yin, Hubery Zhuang, Shaobin Zhu, Huminhao Li, Yinan Qian, Lei Zhang, Chao Zhao, Hanbin Qian, Hui Li, Chen |
| contents | Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into various downstream tasks and theoretical analysis. However, current practices typically approximate the diffusion Fisher by applying auto-differentiation to the learned score network. This black-box method, though straightforward, lacks any accuracy guarantee and is time-consuming. In this paper, we show that the diffusion Fisher actually resides within a space spanned by the outer products of score and initial data. Based on the outer-product structure, we develop two efficient approximation algorithms to access the trace and matrix-vector multiplication of DF, respectively. These algorithms bypass the auto-differentiation operations with time-efficient vector-product calculations. Furthermore, we establish the approximation error bounds for the proposed algorithms. Experiments in likelihood evaluation and adjoint optimization demonstrate the superior accuracy and reduced computational cost of our proposed algorithms. Additionally, based on the novel outer-product formulation of DF, we design the first numerical verification experiment for the optimal transport property of the general PF-ODE deduced map. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23264 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficiently Access Diffusion Fisher: Within the Outer Product Span Space Wang, Fangyikang Yin, Hubery Zhuang, Shaobin Zhu, Huminhao Li, Yinan Qian, Lei Zhang, Chao Zhao, Hanbin Qian, Hui Li, Chen Machine Learning Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into various downstream tasks and theoretical analysis. However, current practices typically approximate the diffusion Fisher by applying auto-differentiation to the learned score network. This black-box method, though straightforward, lacks any accuracy guarantee and is time-consuming. In this paper, we show that the diffusion Fisher actually resides within a space spanned by the outer products of score and initial data. Based on the outer-product structure, we develop two efficient approximation algorithms to access the trace and matrix-vector multiplication of DF, respectively. These algorithms bypass the auto-differentiation operations with time-efficient vector-product calculations. Furthermore, we establish the approximation error bounds for the proposed algorithms. Experiments in likelihood evaluation and adjoint optimization demonstrate the superior accuracy and reduced computational cost of our proposed algorithms. Additionally, based on the novel outer-product formulation of DF, we design the first numerical verification experiment for the optimal transport property of the general PF-ODE deduced map. |
| title | Efficiently Access Diffusion Fisher: Within the Outer Product Span Space |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.23264 |