SOURCE-LINKED INTELLIGENCE

Belted Engression: Sufficient Dimension Reduction for Generative Distributional Regression

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Modern conditional generative models face significant challenges when learning complex covariate dependencies. While sufficient dimension reduction (SDR) provides a principled approach to compress these dependencies, traditional SDR frameworks were not formulated for conditional generation. To bridge this gap, we propose Belted Engression, a unified and architecturally parameter-efficient framework for generative distributional regression. Our approach establishes an end-to-end compress-then-generate paradigm driven by sufficient representation learning, embedding a structural bottleneck into

Read original source ↗ Open in workspace

recordType

paper

region

Global