NeurIPS 2025poster0 citations

Risk Bounds For Distributional Regression

Carlos Misael Madrid Padilla, OSCAR HERNAN MADRID PADILLA, Sabyasachi Chatterjee

Abstract

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.

Nonparametric distribution estimationisotonictrend filteringdense ReLU networks.
BibTeX
@inproceedings{
padilla2025risk,
title={Risk Bounds For Distributional Regression},
author={Carlos Misael Madrid Padilla and OSCAR HERNAN MADRID PADILLA and Sabyasachi Chatterjee},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=Wav9TP5SOR}
}
Risk Bounds For Distributional Regression · NeurIPS 2025