典型文献
Non-asymptotic Error Bound for Optimal Prediction of Function-on-Function Regression by RKHS Approach
文献摘要：
In this paper,we study and analyze the regularized least squares for function-on-function regression model.In our model,both the predictors(input data)and responses(output data)are multivariate functions(with d variables and d variables respectively),and the model coefficient lies in a reproducing kernel Hilbert space(RKHS).We show under mild condition on the reproducing kernel and input data statistics that the convergence rate of excess prediction risk by the regularized least squares is minimax optimal.Numerical examples based on medical image analysis and atmospheric point spread function estimation are considered and tested,and the results demonstrate that the performance of the proposed model is comparable with that of other testing methods.
文献关键词：
中图分类号：
作者姓名：
Hong Zhi TONG;Ling Fang HU;Michael NG
作者机构：
School of Statistics,University of International Business and Economics,Beijing 100029,P.R.China;Department of Mathematics,Hong Kong Baptist University,Kowloon Tong,Hong Kong,P.R.China;Department of Mathematics,The University of Hong Kong,Pokfulam,Hong Kong,P.R.China
文献出处：
引用格式：
[1]Hong Zhi TONG;Ling Fang HU;Michael NG-.Non-asymptotic Error Bound for Optimal Prediction of Function-on-Function Regression by RKHS Approach)[J].数学学报（英文版）,2022(04):777-796
A类：
B类：
Non,asymptotic,Error,Bound,Optimal,Prediction,Function,Regression,by,RKHS,Approach,In,this,paper,we,study,analyze,regularized,least,squares,regression,model,our,both,predictors,input,data,responses,output,multivariate,functions,variables,respectively,coefficient,lies,reproducing,kernel,Hilbert,space,We,show,under,mild,condition,statistics,that,convergence,excess,prediction,risk,minimax,optimal,Numerical,examples,medical,image,analysis,atmospheric,point,spread,estimation,considered,tested,results,demonstrate,performance,proposed,comparable,other,testing,methods
AB值：
0.650712
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
