Sufficiently Reduced Distributional Regression
Abstract
We propose Sufficiently Reduced Distributional Regression (SRDR), a generative method that combines conditional distribution estimation with nonlinear sufficient dimension reduction (SDR). It builds on a characterization of sufficiency through strictly proper scoring rules: a dimension reduction is sufficient if and only if predicting the response from the reduced covariates incurs no loss in expected score relative to the full covariates. Sufficient dimension reduction thus becomes a risk minimization problem. SRDR jointly trains a dimension reduction map and a generative prediction model by minimizing the energy score, which can be estimated by sampling without density evaluation or adversarial training. The framework extends to multi-environment data and to classification. We prove that the estimated conditional distributions converge in energy distance to the true ones, which implies that the learned representation is asymptotically sufficient. In simulations and applications to CT slice localization, superconductivity, and digit classification, SRDR recovers low-dimensional sufficient structure and matches or outperforms state-of-the-art nonlinear SDR methods in representation quality and predictive performance.
Related
- On the Calibration of Isotonic Distributional Regression
- Distributional Regression for Arbitrary Response Variables Using ReLU Neural Networks
- Belted Engression: Sufficient Dimension Reduction for Generative Distributional Regression
- Stochastic Variational Inference for Vine Copula Distributional Regression
- Spatially-Indexed Longitudinal Distributional Outcome Regression for Environmental Monitoring
BibTeX
@misc{henzi2026sufficiently,
title = {{Sufficiently Reduced Distributional Regression}},
author = {Alexander Henzi and Tiange Liu and Xinwei Shen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.29291},
eprint = {2609.29291},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.29291},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Sufficiently Reduced Distributional Regression
AU - Alexander Henzi
AU - Tiange Liu
AU - Xinwei Shen
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2609.29291
UR - https://arxiv.org/abs/2609.29291
AB - We propose Sufficiently Reduced Distributional Regression (SRDR), a generative method that combines conditional distribution estimation with nonlinear sufficient dimension reduction (SDR). It builds on a characterization of sufficiency through strictly proper scoring rules: a dimension reduction is sufficient if and only if predicting the response from the reduced covariates incurs no loss in expected score relative to the full covariates. Sufficient dimension reduction thus becomes a risk minimization problem. SRDR jointly trains a dimension reduction map and a generative prediction model by minimizing the energy score, which can be estimated by sampling without density evaluation or adversarial training. The framework extends to multi-environment data and to classification. We prove that the estimated conditional distributions converge in energy distance to the true ones, which implies that the learned representation is asymptotically sufficient. In simulations and applications to CT slice localization, superconductivity, and digit classification, SRDR recovers low-dimensional sufficient structure and matches or outperforms state-of-the-art nonlinear SDR methods in representation quality and predictive performance.
ER -