Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2305.09605 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929400808734720 |
|---|---|
| author | Vargas, Francisco Reu, Teodora Kerekes, Anna Bronstein, Michael M |
| author_facet | Vargas, Francisco Reu, Teodora Kerekes, Anna Bronstein, Michael M |
| contents | Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transforms the data distribution into a Gaussian. Samples from the generative model are then obtained by simulating an approximation of the time reversal of this diffusion initialized by Gaussian samples. Recent research has explored adapting diffusion models for sampling and inference tasks. In this paper, we leverage known connections to stochastic control akin to the Föllmer drift to extend established neural network approximation results for the Föllmer drift to denoising diffusion models and samplers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_09605 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models Vargas, Francisco Reu, Teodora Kerekes, Anna Bronstein, Michael M Machine Learning Denoising diffusion models are a class of generative models which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transforms the data distribution into a Gaussian. Samples from the generative model are then obtained by simulating an approximation of the time reversal of this diffusion initialized by Gaussian samples. Recent research has explored adapting diffusion models for sampling and inference tasks. In this paper, we leverage known connections to stochastic control akin to the Föllmer drift to extend established neural network approximation results for the Föllmer drift to denoising diffusion models and samplers. |
| title | To smooth a cloud or to pin it down: Guarantees and Insights on Score Matching in Denoising Diffusion Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2305.09605 |