Improved off-policy training of diffusion samplers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913646977744896 |
|---|---|
| author | Sendera, Marcin Kim, Minsu Mittal, Sarthak Lemos, Pablo Scimeca, Luca Rector-Brooks, Jarrid Adam, Alexandre Bengio, Yoshua Malkin, Nikolay |
| author_facet | Sendera, Marcin Kim, Minsu Mittal, Sarthak Lemos, Pablo Scimeca, Luca Rector-Brooks, Jarrid Adam, Alexandre Bengio, Yoshua Malkin, Nikolay |
| contents | We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks). Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work. We also propose a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer, and show that it improves the quality of samples on a variety of target distributions. Our code for the sampling methods and benchmarks studied is made public at https://github.com/GFNOrg/gfn-diffusion as a base for future work on diffusion models for amortized inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05098 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improved off-policy training of diffusion samplers Sendera, Marcin Kim, Minsu Mittal, Sarthak Lemos, Pablo Scimeca, Luca Rector-Brooks, Jarrid Adam, Alexandre Bengio, Yoshua Malkin, Nikolay Machine Learning We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks). Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work. We also propose a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer, and show that it improves the quality of samples on a variety of target distributions. Our code for the sampling methods and benchmarks studied is made public at https://github.com/GFNOrg/gfn-diffusion as a base for future work on diffusion models for amortized inference. |
| title | Improved off-policy training of diffusion samplers |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.05098 |