Generative Modeling with Bayesian Sample Inference
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915756902449152 |
|---|---|
| author | Lienen, Marten Kollovieh, Marcel Günnemann, Stephan |
| author_facet | Lienen, Marten Kollovieh, Marcel Günnemann, Stephan |
| contents | We derive a novel generative model from iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we can formulate the sampling process in the language of Bayesian probability. Our model uses a sequence of prediction and posterior update steps to iteratively narrow down the unknown sample starting from a broad initial belief. In addition to a rigorous theoretical analysis, we establish a connection between our model and diffusion models and show that it includes Bayesian Flow Networks (BFNs) as a special case. In our experiments, we demonstrate that our model improves sample quality on ImageNet32 over both BFNs and the closely related Variational Diffusion Models, while achieving equivalent log-likelihoods on ImageNet32 and ImageNet64. Find our code at https://github.com/martenlienen/bsi. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07580 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative Modeling with Bayesian Sample Inference Lienen, Marten Kollovieh, Marcel Günnemann, Stephan Machine Learning We derive a novel generative model from iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we can formulate the sampling process in the language of Bayesian probability. Our model uses a sequence of prediction and posterior update steps to iteratively narrow down the unknown sample starting from a broad initial belief. In addition to a rigorous theoretical analysis, we establish a connection between our model and diffusion models and show that it includes Bayesian Flow Networks (BFNs) as a special case. In our experiments, we demonstrate that our model improves sample quality on ImageNet32 over both BFNs and the closely related Variational Diffusion Models, while achieving equivalent log-likelihoods on ImageNet32 and ImageNet64. Find our code at https://github.com/martenlienen/bsi. |
| title | Generative Modeling with Bayesian Sample Inference |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.07580 |