arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.04789math.FAcs.LG
收藏

用深度ReLU神经网络逼近$L^p(μ)$

Approximation in $L^p(μ)$ with deep ReLU neural networks

Katholische Universität Eichstätt–Ingolstadt(艾希施泰特-因戈尔施塔特天主教大学);University of Oxford(牛津大学)

Felix Voigtlaender, Philipp Petersen

摘要:

通过分析非光滑ReLU激活函数$\varrho(x) = \max\{0,x\}$的逼近理论性质,讨论了这种神经网络的表达能力。现有的结果主要分为两类:使用具有固定深度的ReLU网络进行近似,或者使用深度随近似精度增加的ReLU网络。回顾这些发现后,我们表明,结果与固定深度的网络--到目前为止只考虑近似在$L^p(λ)$的勒贝格措施$λ$ --可以推广到近似在$L^p(μ)$,任何有限的Borel措施$μ$。特别是,一般的结果适用于统计学习理论的通常设置,其中一个是有兴趣在近似$L^2(\mathbb{P})$,概率测度$\mathbb{P}$描述的数据分布。

英文摘要:

We discuss the expressive power of neural networks which use the non-smooth ReLU activation function $\varrho(x) = \max\{0,x\}$ by analyzing the approximation theoretic properties of such networks. The existing results mainly fall into two categories: approximation using ReLU networks with a fixed depth, or using ReLU networks whose depth increases with the approximation accuracy. After reviewing these findings, we show that the results concerning networks with fixed depth--- which up to now only consider approximation in $L^p(λ)$ for the Lebesgue measure $λ$--- can be generalized to approximation in $L^p(μ)$, for any finite Borel measure $μ$. In particular, the generalized results apply in the usual setting of statistical learning theory, where one is interested in approximation in $L^2(\mathbb{P})$, with the probability measure $\mathbb{P}$ describing the distribution of the data.

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。

↑