分析神经网络实现的条件生成模型误差,给出理论收敛速率。
Error Analysis of Neural-Network-Based Engression

- 将误差分解为近似、随机和蒙特卡洛三部分
- 在组合光滑性假设下证明了收敛速度
- 适合关注生成模型理论保证的研究者
Engression(Shen 和 Meinshausen, 2024)通过能量评分这一严格恰当评分规则,拟合生成模型 $Y = f(X,ε)$ 来学习条件分布。本文对基于深度神经网络实现的 engression 进行理论误差分析。我们将其超额风险分解为近似误差、随机误差和蒙特卡洛误差三个部分。在此分解基础上,假设目标条件生成器具有组合光滑性结构,建立了相应的收敛速率。
原文摘要 · Abstract (English)
Engression (Shen and Meinshausen, 2024) learns a conditional distribution by fitting a generative model $Y = f(X,\varepsilon)$ 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。