Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.19373 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914271440404480 |
|---|---|
| author | Christensen, Sören Kallsen, Jan Strauch, Claudia Trottner, Lukas |
| author_facet | Christensen, Sören Kallsen, Jan Strauch, Claudia Trottner, Lukas |
| contents | We introduce a new class of generative diffusion models that, unlike conventional denoising diffusion models, achieve a time-homogeneous structure for both the noising and denoising processes, allowing the number of steps to adaptively adjust based on the noise level. This is accomplished by conditioning the forward process using Doob's $h$-transform, which terminates the process at a suitable sampling distribution at a random time. The model is particularly well suited for generating data with lower intrinsic dimensions, as the termination criterion simplifies to a first-hitting rule. A key feature of the model is its adaptability to the target data, enabling a variety of downstream tasks using a pre-trained unconditional generative model. These tasks include natural conditioning through appropriate initialisation of the denoising process and classification of noisy data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19373 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Fixed Horizons: A Theoretical Framework for Adaptive Denoising Diffusions Christensen, Sören Kallsen, Jan Strauch, Claudia Trottner, Lukas Machine Learning We introduce a new class of generative diffusion models that, unlike conventional denoising diffusion models, achieve a time-homogeneous structure for both the noising and denoising processes, allowing the number of steps to adaptively adjust based on the noise level. This is accomplished by conditioning the forward process using Doob's $h$-transform, which terminates the process at a suitable sampling distribution at a random time. The model is particularly well suited for generating data with lower intrinsic dimensions, as the termination criterion simplifies to a first-hitting rule. A key feature of the model is its adaptability to the target data, enabling a variety of downstream tasks using a pre-trained unconditional generative model. These tasks include natural conditioning through appropriate initialisation of the denoising process and classification of noisy data. |
| title | Beyond Fixed Horizons: A Theoretical Framework for Adaptive Denoising Diffusions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.19373 |