This paper introduces a general framework for explicitly constructing universal deep neural models with inputs from a complete, separable, and locally-compact metric space $\mathcal{X}$ and outputs in the Wasserstein-1 $\mathcal{P}_1(\mathcal{Y})$ space over a complete and separable metric space $\mathcal{Y}$. We find that any model built using the proposed framework is dense in the space $C(\mathcal{X},\mathcal{P}_1(\mathcal{Y}))$ of continuous functions from $\mathcal{X}$ to $\mathcal{P}_1(\mathcal{Y})$ in the corresponding uniform convergence on compacts topology, quantitatively. We identify two methods in which the curse of dimensionality can be broken. The first approach constructs subsets of $C(\mathcal{X},\mathcal{P}_1(\mathcal{Y}))$ consisting of functions that can be efficiently approximated. In the second approach, given any fixed $f \in C(\mathcal{X},\mathcal{P}_1(\mathcal{Y}))$, we build non-trivial subsets of $\mathcal{X}$ on which $f$ can be efficiently approximated. The results are applied to three open problems lying at the interface of applied probability and computational learning theory. We find that the proposed models can approximate any regular conditional distribution of a $\mathcal{Y}$-valued random element $Y$ depending on an $\mathcal{X}$-valued random element $X$, with arbitrarily high probability. The proposed models are also shown to be capable of generically expressing the aleatoric uncertainty present in most randomized machine learning models. The proposed framework is used to derive an affirmative answer to the open conjecture of Bishop (1994); namely: mixture density networks are generic regular conditional distributions. Numerical experiments are performed in the contexts of extreme learning machines, randomized DNNs, and heteroscedastic regression.

翻译：本文引入了一个用于明确构建通用深度神经模型的一般框架, 其投入来自完整、 可分解 和本地兼容的分子, 空间 $\ mathcal{X} 美元 和瓦塞斯坦-1$\ mathcal{P\1 (mathcal{Y}) 美元空间, 完整且可分解的 空间 $\ mathcal{ Y} 。 我们发现, 任何使用拟议框架构建的模型, 空间 $C (mathcal{X}, 任意=pathal{ pácal{ (mathcal{Y} ), 持续功能$macal $cal_ climate{ 美元 美元 美元, 数字=modemodeal_ a macreal_ dismal_ dismal_ a macreal_ dismal_ dismal_ a preal_ a preal_ a preal_ a promodeal_ a macial_ a messal_ a messal_ a messal_ mode a modeal_ brocial_ a mode a modeal_ modeal_ a mode a mode a modeal_ mode a mode a modeal_ mode a mode a mode a modeal_ modeal_ modeal_ a modeal_ modeal_ modeal_ modeal_ modeal_ modeal_ modeal_ modeal_ momental_ a ma modeal_ modeal_ modeal_ modeal_ mode a a a a a mode a mode a a a mode a mode a modeal_ modeal_ mode a modeal_ moal_ ma a mos a mos a mos a moal_ modeal_ mode a modeal_ mode a mo ma modeal_ ma