We introduce a universal class of geometric deep learning models, called metric hypertransformers (MHTs), capable of approximating any adapted map $F:\mathscr{X}^{\mathbb{Z}}\rightarrow \mathscr{Y}^{\mathbb{Z}}$ with approximable complexity, where $\mathscr{X}\subseteq \mathbb{R}^d$ and $\yyy$ is any suitable metric space, and $\mathscr{X}^{\mathbb{Z}}$ (resp. $\mathscr{Y}^{\mathbb{Z}}$) capture all discrete-time paths on $\mathscr{X}$ (resp. $\mathscr{Y}$). Suitable spaces $\mathscr{Y}$ include various (adapted) Wasserstein spaces, all Fr\'{e}chet spaces admitting a Schauder basis, and a variety of Riemannian manifolds arising from information geometry. Even in the static case, where $f:\mathscr{X}\rightarrow \mathscr{Y}$ is a H\"{o}lder map, our results provide the first (quantitative) universal approximation theorem compatible with any such $\mathscr{X}$ and $\mathscr{Y}$. Our universal approximation theorems are quantitative, and they depend on the regularity of $F$, the choice of activation function, the metric entropy and diameter of $\mathscr{X}$, and on the regularity of the compact set of paths whereon the approximation is performed. Our guiding examples originate from mathematical finance. Notably, the MHT models introduced here are able to approximate a broad range of stochastic processes' kernels, including solutions to SDEs, many processes with arbitrarily long memory, and functions mapping sequential data to sequences of forward rate curves.
翻译:我们引入了一个通用的测深学习模型级, 叫做 立体超导( MHT), 能够代表任何调整过的地图 $F:\ mathscr{X\\\\mathb\\r\\\ mathcr{Y\\\\\\\\\\ mathb{Y\\\\美元, 具有相似的复杂度。 合适的空间 $( mathcr{ ) 和 $\yyy$, 被称为 立体超导{x\xmacr{ mathbrb}, 能够代表所有离散时间路径 $F: mathcr{xr>, 可以提供许多( 适应的) 瓦塞斯坦空间, 所有的Fr\ { { decretreax, 和来自信息几何位置的 Rienrentral 。