Structured Diffusion Models with Mixture of Gaussians as Prior Distribution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917815799250944 |
|---|---|
| author | Jia, Nanshan Zhu, Tingyu Liu, Haoyu Zheng, Zeyu |
| author_facet | Jia, Nanshan Zhu, Tingyu Liu, Haoyu Zheng, Zeyu |
| contents | We propose a class of structured diffusion models, in which the prior distribution is chosen as a mixture of Gaussians, rather than a standard Gaussian distribution. The specific mixed Gaussian distribution, as prior, can be chosen to incorporate certain structured information of the data. We develop a simple-to-implement training procedure that smoothly accommodates the use of mixed Gaussian as prior. Theory is provided to quantify the benefits of our proposed models, compared to the classical diffusion models. Numerical experiments with synthetic, image and operational data are conducted to show comparative advantages of our model. Our method is shown to be robust to mis-specifications and in particular suits situations where training resources are limited or faster training in real time is desired. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_19149 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Structured Diffusion Models with Mixture of Gaussians as Prior Distribution Jia, Nanshan Zhu, Tingyu Liu, Haoyu Zheng, Zeyu Machine Learning We propose a class of structured diffusion models, in which the prior distribution is chosen as a mixture of Gaussians, rather than a standard Gaussian distribution. The specific mixed Gaussian distribution, as prior, can be chosen to incorporate certain structured information of the data. We develop a simple-to-implement training procedure that smoothly accommodates the use of mixed Gaussian as prior. Theory is provided to quantify the benefits of our proposed models, compared to the classical diffusion models. Numerical experiments with synthetic, image and operational data are conducted to show comparative advantages of our model. Our method is shown to be robust to mis-specifications and in particular suits situations where training resources are limited or faster training in real time is desired. |
| title | Structured Diffusion Models with Mixture of Gaussians as Prior Distribution |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.19149 |