生成式自助法过程
Generative bootstrap processes
浏览论文内容
中文总结 AI 辅助
本文研究从拟合生成分布重采样得到的生成式自助法过程,给出其条件弱收敛到P-布朗桥的充要条件及Giné-Zinn型刻画,并验证了多类生成模型满足这些条件。
中文摘要 AI 辅助
我们研究了通过从拟合的生成分布中重采样而获得的生成式自助法过程。我们建立了其条件弱收敛到$P$-布朗桥的充分必要条件,这些条件以有限维条件弱收敛和条件渐近等连续性的形式表述。我们进一步提供了通用充分条件,以及一个Giné-Zinn型刻画,将该收敛性与$P$-Donsker性质联系起来。作为应用,我们验证了这些条件适用于几类重要的生成模型,包括三角归一化流、流匹配、基于分数的扩散模型和Wasserstein生成对抗网络。
英文摘要
We study generative bootstrap processes obtained by resampling from fitted generative distributions. We establish necessary and sufficient conditions for their conditional weak convergence to the $P$-Brownian bridge, formulated in terms of finite-dimensional conditional weak convergence and conditional asymptotic equicontinuity. We further provide general sufficient conditions and a Giné-Zinn-type characterization relating this convergence to the $P$-Donsker property. As applications, we verify these conditions for prominent classes of generative models, including triangular normalizing flows, flow matching, score-based diffusion models, and Wasserstein generative adversarial networks.
发表机构
- University of Washington(华盛顿大学)
机构由 AI 辅助整理,请以论文原文为准。