Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Lai, Jianfa"'
Kernel methods are widely used in machine learning, especially for classification problems. However, the theoretical analysis of kernel classification is still limited. This paper investigates the statistical performances of kernel classifiers. With
Externí odkaz:
http://arxiv.org/abs/2402.01148
In this paper, we study the generalization ability of the wide residual network on $\mathbb{S}^{d-1}$ with the ReLU activation function. We first show that as the width $m\rightarrow\infty$, the residual network kernel (RNK) uniformly converges to th
Externí odkaz:
http://arxiv.org/abs/2305.18506
We perform a study on the generalization ability of the wide two-layer ReLU neural network on $\mathbb{R}$. We first establish some spectral properties of the neural tangent kernel (NTK): $a)$ $K_{d}$, the NTK defined on $\mathbb{R}^{d}$, is positive
Externí odkaz:
http://arxiv.org/abs/2302.05933
Publikováno v:
Communications in Statistics - Simulation and Computation 2021
The construction of uniform designs (UDs) has received much attention in computer experiments over the past decades, but most of the previous works obtain uniform designs over a U-type by lattice domain. Due to increasing demands for continuous facto
Externí odkaz:
http://arxiv.org/abs/2301.10366
Construction of symmetric orthogonal designs with deep Q-network and orthogonal complementary design
Publikováno v:
In Computational Statistics and Data Analysis July 2022 171
Autor:
Lai, Jianfa1,2 (AUTHOR), Fang, Kai-Tai3,4 (AUTHOR), Peng, Xiaoling3 (AUTHOR), Lin, Yuxuan3 (AUTHOR) yuxuanlin@uic.edu.cn
Publikováno v:
Communications in Statistics: Simulation & Computation. 2024, Vol. 53 Issue 1, p130-146. 17p.
Publikováno v:
Communications in Statistics - Simulation and Computation. :1-17
The construction of uniform designs (UDs) has received much attention in computer experiments over the past decades, but most of the previous works obtain uniform designs over a U-type by lattice domain. Due to increasing demands for continuous facto