Research
Error Analysis of Neural-Network-Based Engression
arXiv:2607.27723v1 Announce Type: cross Abstract: Engression (Shen and Meinshausen, 2024) learns a conditional distribution by fitting a generative model Y = f(X,arepsilon) under the energy score, a s
arXiv:2607.27723v1 Announce Type: cross Abstract: Engression (Shen and Meinshausen, 2024) learns a conditional distribution by fitting a generative model Y = f(X,arepsilon) under the energy score, a strictly proper scoring rule. We provide a theoretical error analysis of engression implemented with deep neural networks. We decompose the excess risk into three components: the approximation error, the stochastic error, and the Monte Carlo error. Based on this decomposition, we establish convergence rates under the assumption that the target conditional generator admits a compositional smoothness structure.
Related
- Theoretical Analysis of Engression and Reverse Markov Engression
- A Diffusive Classification Loss for Learning Energy-based Generative Models
- Energy-based models for diagnostic reconstruction and analysis in a laboratory plasma device
- From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting
Source: arXiv cs.LG | 2026-07-31