Kernel Matrix Regularization via Shrinkage Estimation

2018 ◽  
pp. 1292-1305
Author(s):  
Tomer Lancewicki
Keyword(s):  
Kernel Matrix ◽  
Shrinkage Estimation ◽  
Matrix Regularization

scholarly journals Nonlinear shrinkage estimation of large integrated covariance matrices

Biometrika ◽  
2017 ◽  
Vol 104 (2) ◽  
pp. 481-488 ◽  
Author(s):  
Clifford Lam ◽  
Phoenix Feng ◽  
Charlie Hu
Keyword(s):  
Covariance Matrices ◽  
Shrinkage Estimation ◽  
Integrated Covariance

scholarly journals Shrinkage estimation of varying covariate effects based on quantile regression

2013 ◽  
Vol 24 (5) ◽  
pp. 853-869 ◽  
Author(s):  
Limin Peng ◽  
Jinfeng Xu ◽  
Nancy Kutner
Keyword(s):  
Quantile Regression ◽  
Shrinkage Estimation ◽  
Covariate Effects

Numerical simulation of squeezing Cu–Water nanofluid flow by a kernel-based method

2021 ◽  
pp. 2250005
Author(s):  
Mojtaba Fardi ◽  
Yasir Khan
Keyword(s):  
Numerical Simulation ◽  
Hilbert Space ◽  
Linear System ◽  
Numerical Simulations ◽  
Numerical Results ◽  
Kernel Matrix ◽  
Nanofluid Flow ◽  
Parallel Disks ◽  
Engineering Problems ◽  
Well Conditioning

The main aim of this paper is to propose a kernel-based method for solving the problem of squeezing Cu–Water nanofluid flow between parallel disks. Our method is based on Gaussian Hilbert–Schmidt SVD (HS-SVD), which gives an alternate basis for the data-dependent subspace of “native” Hilbert space without ever forming kernel matrix. The well-conditioning linear system is one of the critical advantages of using the alternate basis obtained from HS-SVD. Numerical simulations are performed to illustrate the efficiency and applicability of the proposed method in the sense of accuracy. Numerical results obtained by the proposed method are assessed by comparing available results in references. The results demonstrate that the proposed method can be recommended as a good option to study the squeezing nanofluid flow in engineering problems.

Sign in / Sign up

Export Citation Format

Share Document