Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.10190 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917331313098752 |
|---|---|
| author | Gottschling, Nina Maria Caprio, Michele |
| author_facet | Gottschling, Nina Maria Caprio, Michele |
| contents | We establish Hoeffding-type concentration inequalities for the low and high tail bounds of sums of exchangeable random variables. Our results exhibit an anti-symmetry in such tail bounds due to the assumption of exchangeability, a generalization of the i.i.d. setting. In contrast to the existing literature on this problem, our result provides an upper tail bound with respect to the largest mean of a distribution in the support of the de Finetti mixing measure, and not the population mean. Equivalently, we establish a lower tail bound with respect to the smallest mean of a distribution in the support of the de Finetti mixing measure. This bridges the gap between finite sample and population means of exchangeable random variables, and distributional means. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10190 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hoeffding-Style Concentration Bounds for Exchangeable Random Variables Gottschling, Nina Maria Caprio, Michele Optimization and Control Probability 60G09, 60F10 We establish Hoeffding-type concentration inequalities for the low and high tail bounds of sums of exchangeable random variables. Our results exhibit an anti-symmetry in such tail bounds due to the assumption of exchangeability, a generalization of the i.i.d. setting. In contrast to the existing literature on this problem, our result provides an upper tail bound with respect to the largest mean of a distribution in the support of the de Finetti mixing measure, and not the population mean. Equivalently, we establish a lower tail bound with respect to the smallest mean of a distribution in the support of the de Finetti mixing measure. This bridges the gap between finite sample and population means of exchangeable random variables, and distributional means. |
| title | Hoeffding-Style Concentration Bounds for Exchangeable Random Variables |
| topic | Optimization and Control Probability 60G09, 60F10 |
| url | https://arxiv.org/abs/2603.10190 |