no code implementations • 13 Jul 2023 • Shijun Zhang, Jianfeng Lu, Hongkai Zhao
This paper explores the expressive power of deep neural networks for a diverse range of activation functions.
no code implementations • 29 Jun 2023 • Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou
In this work, a comprehensive numerical study involving analysis and experiments shows why a two-layer neural network has difficulties handling high frequencies in approximation and learning when machine precision and computation cost are important factors in real practice.
no code implementations • 29 Jan 2023 • Shijun Zhang, Jianfeng Lu, Hongkai Zhao
This paper explores the expressive power of deep neural networks through the framework of function compositions.
no code implementations • 19 May 2022 • Zuowei Shen, Haizhao Yang, Shijun Zhang
It is proved by construction that height-$s$ ReLU NestNets with $\mathcal{O}(n)$ parameters can approximate $1$-Lipschitz continuous functions on $[0, 1]^d$ with an error $\mathcal{O}(n^{-(s+1)/d})$, while the optimal approximation error of standard ReLU networks with $\mathcal{O}(n)$ parameters is $\mathcal{O}(n^{-2/d})$.
no code implementations • 15 Nov 2021 • Zuowei Shen, Haizhao Yang, Shijun Zhang
Furthermore, we show that the idea of learning a small number of parameters to achieve a good approximation can be numerically observed.
no code implementations • 6 Jul 2021 • Zuowei Shen, Haizhao Yang, Shijun Zhang
This paper develops simple feed-forward neural networks that achieve the universal approximation property for all continuous functions with a fixed finite number of neurons.
no code implementations • 28 Feb 2021 • Zuowei Shen, Haizhao Yang, Shijun Zhang
This paper concentrates on the approximation power of deep feed-forward neural networks in terms of width and depth.
no code implementations • 25 Oct 2020 • Zuowei Shen, Haizhao Yang, Shijun Zhang
A three-hidden-layer neural network with super approximation power is introduced.
no code implementations • 22 Jun 2020 • Zuowei Shen, Haizhao Yang, Shijun Zhang
More generally for an arbitrary continuous function $f$ on $[0, 1]^d$ with a modulus of continuity $\omega_f(\cdot)$, the constructive approximation rate is $\omega_f(\sqrt{d}\, N^{-\sqrt{L}})+2\omega_f(\sqrt{d}){N^{-\sqrt{L}}}$.
no code implementations • 9 Jan 2020 • Jianfeng Lu, Zuowei Shen, Haizhao Yang, Shijun Zhang
This paper establishes the (nearly) optimal approximation error characterization of deep rectified linear unit (ReLU) networks for smooth functions in terms of both width and depth simultaneously.
no code implementations • 13 Jun 2019 • Zuowei Shen, Haizhao Yang, Shijun Zhang
This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons.
no code implementations • 26 Feb 2019 • Zuowei Shen, Haizhao Yang, Shijun Zhang
In particular, for any function $f$ on $[0, 1]$, regardless of its smoothness and even the continuity, if $f$ can be approximated using a dictionary when $L=1$ with the best $N$-term approximation rate $\varepsilon_{L, f}={\cal O}(N^{-\eta})$, we show that dictionaries with $L=2$ can improve the best $N$-term approximation rate to $\varepsilon_{L, f}={\cal O}(N^{-2\eta})$.