Jeffrey's update rule as a minimizer of Kullback-Leibler divergence
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916624867524608 |
|---|---|
| author | Pinzón, Carlos Palamidessi, Catuscia |
| author_facet | Pinzón, Carlos Palamidessi, Catuscia |
| contents | In this paper, we show a more concise and high level proof than the original one, derived by researcher Bart Jacobs, for the following theorem: in the context of Bayesian update rules for learning or updating internal states that produce predictions, the relative entropy between the observations and the predictions is reduced when applying Jeffrey's update rule to update the internal state. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15504 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Jeffrey's update rule as a minimizer of Kullback-Leibler divergence Pinzón, Carlos Palamidessi, Catuscia Machine Learning Cryptography and Security In this paper, we show a more concise and high level proof than the original one, derived by researcher Bart Jacobs, for the following theorem: in the context of Bayesian update rules for learning or updating internal states that produce predictions, the relative entropy between the observations and the predictions is reduced when applying Jeffrey's update rule to update the internal state. |
| title | Jeffrey's update rule as a minimizer of Kullback-Leibler divergence |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2502.15504 |