Optimal Budgeted Rejection Sampling for Generative Models
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_ | 1866911786960158720 |
|---|---|
| author | Verine, Alexandre Pydi, Muni Sreenivas Negrevergne, Benjamin Chevaleyre, Yann |
| author_facet | Verine, Alexandre Pydi, Muni Sreenivas Negrevergne, Benjamin Chevaleyre, Yann |
| contents | Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models. However, these methods are only optimal under an unlimited sampling budget, and are usually applied to a generator trained independently of the rejection procedure. We first propose an Optimal Budgeted Rejection Sampling (OBRS) scheme that is provably optimal with respect to \textit{any} $f$-divergence between the true distribution and the post-rejection distribution, for a given sampling budget. Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance. Through experiments and supporting theory, we show that the proposed methods are effective in significantly improving the quality and diversity of the samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_00460 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Optimal Budgeted Rejection Sampling for Generative Models Verine, Alexandre Pydi, Muni Sreenivas Negrevergne, Benjamin Chevaleyre, Yann Machine Learning Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models. However, these methods are only optimal under an unlimited sampling budget, and are usually applied to a generator trained independently of the rejection procedure. We first propose an Optimal Budgeted Rejection Sampling (OBRS) scheme that is provably optimal with respect to \textit{any} $f$-divergence between the true distribution and the post-rejection distribution, for a given sampling budget. Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance. Through experiments and supporting theory, we show that the proposed methods are effective in significantly improving the quality and diversity of the samples. |
| title | Optimal Budgeted Rejection Sampling for Generative Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2311.00460 |