Metraipolis › archive › dc_ffe73c0771dd
Sufficiently Reduced Distributional Regression — arXiv:2609.29291
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29291
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T05:26:31.358Z
- SHA-256 of the archived text
a814f0edeb18ff34d6a98407d3aa7088236d9ffdbe89d8d32c092cec2980da4b- Stable URL of this page
https://metraipolis.com/documento/dc_ffe73c0771dd
How to cite
Sufficiently Reduced Distributional Regression — arXiv:2609.29291 — arXiv (en), https://arxiv.org/abs/2609.29291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ffe73c0771dd (Metraipolis archive dc_ffe73c0771dd, sha256 a814f0edeb18ff34d6a98407d3aa7088236d9ffdbe89d8d32c092cec2980da4b)
BibTeX
@misc{dcffe73c0771dd,
title = {Sufficiently Reduced Distributional Regression — arXiv:2609.29291},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29291},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ffe73c0771dd; sha256 a814f0edeb18ff34d6a98407d3aa7088236d9ffdbe89d8d32c092cec2980da4b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG). Categorie arXiv: Methodology (stat.ME) ; Machine Learning (cs.LG); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.29291 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:50:39.648Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).