Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.20175 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916773368954880 |
|---|---|
| author | Zheng, Hongkai Chu, Wenda Wang, Austin Kovachki, Nikola Baptista, Ricardo Yue, Yisong |
| author_facet | Zheng, Hongkai Chu, Wenda Wang, Austin Kovachki, Nikola Baptista, Ricardo Yue, Yisong |
| contents | When solving inverse problems, one increasingly popular approach is to use pre-trained diffusion models as plug-and-play priors. This framework can accommodate different forward models without re-training while preserving the generative capability of diffusion models. Despite their success in many imaging inverse problems, most existing methods rely on privileged information such as derivative, pseudo-inverse, or full knowledge about the forward model. This reliance poses a substantial limitation that restricts their use in a wide range of problems where such information is unavailable, such as in many scientific applications. We propose Ensemble Kalman Diffusion Guidance (EnKG), a derivative-free approach that can solve inverse problems by only accessing forward model evaluations and a pre-trained diffusion model prior. We study the empirical effectiveness of EnKG across various inverse problems, including scientific settings such as inferring fluid flows and astronomical objects, which are highly non-linear inverse problems that often only permit black-box access to the forward model. We open-source our code at https://github.com/devzhk/enkg-pytorch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_20175 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems Zheng, Hongkai Chu, Wenda Wang, Austin Kovachki, Nikola Baptista, Ricardo Yue, Yisong Machine Learning When solving inverse problems, one increasingly popular approach is to use pre-trained diffusion models as plug-and-play priors. This framework can accommodate different forward models without re-training while preserving the generative capability of diffusion models. Despite their success in many imaging inverse problems, most existing methods rely on privileged information such as derivative, pseudo-inverse, or full knowledge about the forward model. This reliance poses a substantial limitation that restricts their use in a wide range of problems where such information is unavailable, such as in many scientific applications. We propose Ensemble Kalman Diffusion Guidance (EnKG), a derivative-free approach that can solve inverse problems by only accessing forward model evaluations and a pre-trained diffusion model prior. We study the empirical effectiveness of EnKG across various inverse problems, including scientific settings such as inferring fluid flows and astronomical objects, which are highly non-linear inverse problems that often only permit black-box access to the forward model. We open-source our code at https://github.com/devzhk/enkg-pytorch. |
| title | Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.20175 |