Non-asymptotic Properties of Generalized Mondrian Forests in Statistical Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913708874137600 |
|---|---|
| author | Zhan, Haoran Wang, Jingli Xia, Yingcun |
| author_facet | Zhan, Haoran Wang, Jingli Xia, Yingcun |
| contents | Random Forests have been extensively used in regression and classification, inspiring the development of various forest-based methods. Among these, Mondrian Forests, derived from the Mondrian process, mark a significant advancement. Expanding on Mondrian Forests, this paper presents a general framework for statistical learning, encompassing a range of common learning tasks such as least squares regression, $\ell_1$ regression, quantile regression, and classification. Under mild assumptions on the loss functions, we provide upper bounds on the regret/risk functions for the estimators and demonstrate their statistical consistency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00660 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Non-asymptotic Properties of Generalized Mondrian Forests in Statistical Learning Zhan, Haoran Wang, Jingli Xia, Yingcun Statistics Theory Random Forests have been extensively used in regression and classification, inspiring the development of various forest-based methods. Among these, Mondrian Forests, derived from the Mondrian process, mark a significant advancement. Expanding on Mondrian Forests, this paper presents a general framework for statistical learning, encompassing a range of common learning tasks such as least squares regression, $\ell_1$ regression, quantile regression, and classification. Under mild assumptions on the loss functions, we provide upper bounds on the regret/risk functions for the estimators and demonstrate their statistical consistency. |
| title | Non-asymptotic Properties of Generalized Mondrian Forests in Statistical Learning |
| topic | Statistics Theory |
| url | https://arxiv.org/abs/2406.00660 |