Saved in:
Bibliographic Details
Main Authors: Angelim, Felipe, Leite, Alessandro
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.04042
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914554940751872
author Angelim, Felipe
Leite, Alessandro
author_facet Angelim, Felipe
Leite, Alessandro
contents We propose Partition Tree, a novel tree-based framework for conditional density estimation over general outcome spaces that supports both continuous and categorical variables within a unified formulation. Our approach models conditional distributions as piecewise-constant densities on data-adaptive partitions and learns trees by directly minimizing conditional negative log-likelihood. This yields a scalable, nonparametric alternative to existing probabilistic trees that does not make parametric assumptions about the target distribution. We further introduce Partition Forest, a bagging extension obtained by averaging conditional densities. Empirically, we demonstrate improved probabilistic prediction over CART-style trees and competitive performance compared to state-of-the-art probabilistic tree methods and Random Forests.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04042
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Partition Tree: Conditional Density Estimation over General Outcome Spaces
Angelim, Felipe
Leite, Alessandro
Machine Learning
Methodology
We propose Partition Tree, a novel tree-based framework for conditional density estimation over general outcome spaces that supports both continuous and categorical variables within a unified formulation. Our approach models conditional distributions as piecewise-constant densities on data-adaptive partitions and learns trees by directly minimizing conditional negative log-likelihood. This yields a scalable, nonparametric alternative to existing probabilistic trees that does not make parametric assumptions about the target distribution. We further introduce Partition Forest, a bagging extension obtained by averaging conditional densities. Empirically, we demonstrate improved probabilistic prediction over CART-style trees and competitive performance compared to state-of-the-art probabilistic tree methods and Random Forests.
title Partition Tree: Conditional Density Estimation over General Outcome Spaces
topic Machine Learning
Methodology
url https://arxiv.org/abs/2602.04042