Several problems in stochastic analysis are defined through their geometry, and preserving that geometric structure is essential to generating meaningful predictions. Nevertheless, how to design principled deep learning (DL) models capable of encoding these geometric structures remains largely unknown. We address this open problem by introducing a universal causal geometric DL framework in which the user specifies a suitable pair of geometries $\mathscr{X}$ and $\mathscr{Y}$ and our framework returns a DL model capable of causally approximating any ``regular'' map sending time series in $\mathscr{X}^{\mathbb{Z}}$ to time series in $\mathscr{Y}^{\mathbb{Z}}$ while respecting their forward flow of information throughout time. Suitable geometries on $\mathscr{Y}$ include various (adapted) Wasserstein spaces arising in optimal stopping problems, a variety of statistical manifolds describing the conditional distribution of continuous-time finite state Markov chains, and all Fr\'echet spaces admitting a Schauder basis, e.g. as in classical finance. Suitable, $\mathscr{X}$ are any compact subset of any Euclidean space. Our results all quantitatively express the number of parameters needed for our DL model to achieve a given approximation error as a function of the target map's regularity and the geometric structure both of $\mathscr{X}$ and of $\mathscr{Y}$. Even when omitting any temporal structure, our universal approximation theorems are the first guarantees that H\"older functions, defined between such $\mathscr{X}$ and $\mathscr{Y}$ can be approximated by DL models.
翻译:透视分析中的一些问题 通过几何来定义 { 字形分析中的一些问题 { 和 $\ mathscr{ Y} 和我们的框架返回一个 DL 模型, 能够因果接近任何“ 常规” 目标在$mathscr{ X\\ mathbb} 和$\ mathcr{ Y} 中发送时间序列的地图。 尽管如此, 如何设计能将这些几何结构编码的深层次学习( DL) 模型仍然基本上未知。 我们通过引入一个通用的因因果的 DL 框架来解决这个未解决的问题, 其中用户指定了一对适合的几对称 $\ mathscr{ X} 和$\ mathr{ Y} 问题, 各种能因果性地标值在$xxxx 标值的基底值之间, 所有Fr\\ checkel 空间中都承认 $xx 的直径基数, egrxxx mell\ crows 。