From Denoising Diffusions to Denoising Markov Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910335473025024 |
|---|---|
| author | Benton, Joe Shi, Yuyang De Bortoli, Valentin Deligiannidis, George Doucet, Arnaud |
| author_facet | Benton, Joe Shi, Yuyang De Bortoli, Valentin Deligiannidis, George Doucet, Arnaud |
| contents | Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising process to obtain synthetic datapoints. The denoising diffusion relies on approximations of the logarithmic derivatives of the noised data densities using score matching. Such models can also be used to perform approximate posterior simulation when one can only sample from the prior and likelihood. We propose a unifying framework generalising this approach to a wide class of spaces and leading to an original extension of score matching. We illustrate the resulting models on various applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_03595 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | From Denoising Diffusions to Denoising Markov Models Benton, Joe Shi, Yuyang De Bortoli, Valentin Deligiannidis, George Doucet, Arnaud Machine Learning Denoising diffusions are state-of-the-art generative models exhibiting remarkable empirical performance. They work by diffusing the data distribution into a Gaussian distribution and then learning to reverse this noising process to obtain synthetic datapoints. The denoising diffusion relies on approximations of the logarithmic derivatives of the noised data densities using score matching. Such models can also be used to perform approximate posterior simulation when one can only sample from the prior and likelihood. We propose a unifying framework generalising this approach to a wide class of spaces and leading to an original extension of score matching. We illustrate the resulting models on various applications. |
| title | From Denoising Diffusions to Denoising Markov Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2211.03595 |