arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.12353cs.LGmath.PRmath.STstat.MLstat.TH
收藏

关于深度生成网络逼近分布的能力

On the capacity of deep generative networks for approximating distributions

The Hong Kong University of Science and Technology(香港科技大学);Huawei Technologies Co., Ltd.(华为技术有限公司)

Yunfei Yang, Zhen Li, Yang Wang

AI总结:

本文从理论上分析了深度生成网络逼近分布的能力,证明在Wasserstein距离和最大均值差异下低维源分布可逼近高维目标分布且误差上界由网络宽度与深度决定,而在f-散度下源分布维度不能低于目标分布的内在维度。

摘要:

我们研究深度生成网络在逼近概率分布方面的有效性与效率。我们证明,当以Wasserstein距离和最大均值差异度量接近程度时,神经网络可以将低维源分布变换为任意接近高维目标分布的分布。逼近误差的上界以神经网络的宽度和深度给出。此外,研究表明Wasserstein距离下的逼近误差至多随环境维度线性增长,且逼近阶数仅取决于目标分布的内在维度。相反,当使用f-散度作为分布度量时,逼近性质有所不同。我们证明,为了在f-散度意义下逼近目标分布,源分布的维度不能小于目标分布的内在维度。

英文摘要:

We study the efficacy and efficiency of deep generative networks for approximating probability distributions. We prove that neural networks can transform a low-dimensional source distribution to a distribution that is arbitrarily close to a high-dimensional target distribution, when the closeness are measured by Wasserstein distances and maximum mean discrepancy. Upper bounds of the approximation error are obtained in terms of the width and depth of neural network. Furthermore, it is shown that the approximation error in Wasserstein distance grows at most linearly on the ambient dimension and that the approximation order only depends on the intrinsic dimension of the target distribution. On the contrary, when $f$-divergences are used as metrics of distributions, the approximation property is different. We show that in order to approximate the target distribution in $f$-divergences, the dimension of the source distribution cannot be smaller than the intrinsic dimension of the target distribution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑