Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914876672180224 |
|---|---|
| author | Altekrüger, Fabian Hagemann, Paul Steidl, Gabriele |
| author_facet | Altekrüger, Fabian Hagemann, Paul Steidl, Gabriele |
| contents | Conditional generative models became a very powerful tool to sample from Bayesian inverse problem posteriors. It is well-known in classical Bayesian literature that posterior measures are quite robust with respect to perturbations of both the prior measure and the negative log-likelihood, which includes perturbations of the observations. However, to the best of our knowledge, the robustness of conditional generative models with respect to perturbations of the observations has not been investigated yet. In this paper, we prove for the first time that appropriately learned conditional generative models provide robust results for single observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_15845 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems Altekrüger, Fabian Hagemann, Paul Steidl, Gabriele Machine Learning Statistics Theory Conditional generative models became a very powerful tool to sample from Bayesian inverse problem posteriors. It is well-known in classical Bayesian literature that posterior measures are quite robust with respect to perturbations of both the prior measure and the negative log-likelihood, which includes perturbations of the observations. However, to the best of our knowledge, the robustness of conditional generative models with respect to perturbations of the observations has not been investigated yet. In this paper, we prove for the first time that appropriately learned conditional generative models provide robust results for single observations. |
| title | Conditional Generative Models are Provably Robust: Pointwise Guarantees for Bayesian Inverse Problems |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2303.15845 |