菜单

关于 🐙 GitHub
arXiv 提交日期: 2026-03-10
📄 Abstract - Global universality via discrete-time signatures

We establish global universal approximation theorems on spaces of piecewise linear paths, stating that linear functionals of the corresponding signatures are dense with respect to $L^p$- and weighted norms, under an integrability condition on the underlying weight function. As an application, we show that piecewise linear interpolations of Brownian motion satisfies this integrability condition. Consequently, we obtain $L^p$-approximation results for path-dependent functionals, random ordinary differential equations, and stochastic differential equations driven by Brownian motion.

顶级标签: theory machine learning
详细标签: signature methods universal approximation path functionals stochastic processes rough paths 或 搜索:

通过离散时间特征实现全局普适性 / Global universality via discrete-time signatures


1️⃣ 一句话总结

这篇论文证明了,对于分段线性路径,其路径特征(signature)的线性泛函在满足一定可积条件下,能够以高精度逼近一大类路径相关的函数和方程,包括布朗运动驱动的随机微分方程,从而为复杂路径数据的建模和分析提供了一个强大的通用逼近工具。

源自 arXiv: 2603.09773