Saved in:
Bibliographic Details
Main Authors: Padilla, Carlos Misael Madrid, Padilla, Oscar Hernan Madrid, Chatterjee, Sabyasachi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.09075
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913938712559616
author Padilla, Carlos Misael Madrid
Padilla, Oscar Hernan Madrid
Chatterjee, Sabyasachi
author_facet Padilla, Carlos Misael Madrid
Padilla, Oscar Hernan Madrid
Chatterjee, Sabyasachi
contents This work examines risk bounds for nonparametric distributional regression estimators. For convex-constrained distributional regression, general upper bounds are established for the continuous ranked probability score (CRPS) and the worst-case mean squared error (MSE) across the domain. These theoretical results are applied to isotonic and trend filtering distributional regression, yielding convergence rates consistent with those for mean estimation. Furthermore, a general upper bound is derived for distributional regression under non-convex constraints, with a specific application to neural network-based estimators. Comprehensive experiments on both simulated and real data validate the theoretical contributions, demonstrating their practical effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09075
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Risk Bounds For Distributional Regression
Padilla, Carlos Misael Madrid
Padilla, Oscar Hernan Madrid
Chatterjee, Sabyasachi
Machine Learning
This work examines risk bounds for nonparametric distributional regression estimators. For convex-constrained distributional regression, general upper bounds are established for the continuous ranked probability score (CRPS) and the worst-case mean squared error (MSE) across the domain. These theoretical results are applied to isotonic and trend filtering distributional regression, yielding convergence rates consistent with those for mean estimation. Furthermore, a general upper bound is derived for distributional regression under non-convex constraints, with a specific application to neural network-based estimators. Comprehensive experiments on both simulated and real data validate the theoretical contributions, demonstrating their practical effectiveness.
title Risk Bounds For Distributional Regression
topic Machine Learning
url https://arxiv.org/abs/2505.09075