Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2504.17008 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917997091749888 |
|---|---|
| author | Kobayashi, Masahiro |
| author_facet | Kobayashi, Masahiro |
| contents | In this study, we discuss the relationship between two families of density-power-based divergences with functional degrees of freedom -- the Hölder divergence and the functional density power divergence (FDPD) -- based on their intersection and generalization. These divergence families include the density power divergence and the $γ$-divergence as special cases. First, we prove that the intersection of the Hölder divergence and the FDPD is limited to a general divergence family introduced by Jones et al. (Biometrika, 2001). Subsequently, motivated by the fact that Hölder's inequality is used in the proofs of nonnegativity for both the Hölder divergence and the FDPD, we define a generalized divergence family, referred to as the $ξ$-Hölder divergence. The nonnegativity of the $ξ$-Hölder divergence is established through a combination of the inequalities used to prove the nonnegativity of the Hölder divergence and the FDPD. Furthermore, we derive an inequality between the composite scoring rules corresponding to different FDPDs based on the $ξ$-Hölder divergence. Finally, we prove that imposing the mathematical structure of the Hölder score on a composite scoring rule results in the $ξ$-Hölder divergence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17008 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Relationship between Hölder Divergence and Functional Density Power Divergence: Intersection and Generalization Kobayashi, Masahiro Information Theory Statistics Theory Machine Learning In this study, we discuss the relationship between two families of density-power-based divergences with functional degrees of freedom -- the Hölder divergence and the functional density power divergence (FDPD) -- based on their intersection and generalization. These divergence families include the density power divergence and the $γ$-divergence as special cases. First, we prove that the intersection of the Hölder divergence and the FDPD is limited to a general divergence family introduced by Jones et al. (Biometrika, 2001). Subsequently, motivated by the fact that Hölder's inequality is used in the proofs of nonnegativity for both the Hölder divergence and the FDPD, we define a generalized divergence family, referred to as the $ξ$-Hölder divergence. The nonnegativity of the $ξ$-Hölder divergence is established through a combination of the inequalities used to prove the nonnegativity of the Hölder divergence and the FDPD. Furthermore, we derive an inequality between the composite scoring rules corresponding to different FDPDs based on the $ξ$-Hölder divergence. Finally, we prove that imposing the mathematical structure of the Hölder score on a composite scoring rule results in the $ξ$-Hölder divergence. |
| title | Relationship between Hölder Divergence and Functional Density Power Divergence: Intersection and Generalization |
| topic | Information Theory Statistics Theory Machine Learning |
| url | https://arxiv.org/abs/2504.17008 |