- Title
- Binary space partitioning forests
- Creator
- Fan, Xuhui; Li, Bin; Sisson, Scott
- Relation
- The 22nd International Conference on Artificial Intelligence and Statistics. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics 2019 (Okinawa, Japan 16 - 18 April, 2019)
- Relation
- http://proceedings.mlr.press/v89/
- Publisher
- The Society for AI and Statistics
- Resource Type
- conference paper
- Date
- 2020
- Description
- The Binary Space Partitioning (BSP)-Tree process is proposed to produce flexible 2-D partition structures which are originally used as a Bayesian nonparametric prior for relational modelling. It can hardly be applied to other learning tasks such as regression trees because extending the BSP-Tree process to a higher dimensional space is nontrivial. This paper is the first attempt to extend the BSP-Tree process to a ddimensional (d > 2) space. We propose to generate a cutting hyperplane, which is assumed to be parallel to d − 2 dimensions, to cut each node in the d-dimensional BSP-tree. By designing a subtle strategy to sample two free dimensions from d dimensions, the extended BSP-Tree process can inherit the essential self-consistency property from the original version. Based on the extended BSP-Tree process, an ensemble model, which is named the BSP-Forest, is further developed for regression tasks. Thanks to the retained self-consistency property, we can thus significantly reduce the geometric calculations in the inference stage. Compared to its counterpart, the Mondrian Forest, the BSP-Forest can achieve similar performance with fewer cuts due to its flexibility. The BSP-Forest also outperforms other (Bayesian) regression forests on a number of real-world data sets.
- Subject
- binary space partitioning; forest; modelling
- Identifier
- http://hdl.handle.net/1959.13/1441673
- Identifier
- uon:41495
- Language
- eng
- Reviewed
- Hits: 780
- Visitors: 780
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|