This paper presents learning rates for the least-square regularized regression algorithms with polynomial kernels. The target is the error analysis for the regression problem in learning theory. A regularization schem...This paper presents learning rates for the least-square regularized regression algorithms with polynomial kernels. The target is the error analysis for the regression problem in learning theory. A regularization scheme is given, which yields sharp learning rates. The rates depend on the dimension of polynomial space and polynomial reproducing kernel Hilbert space measured by covering numbers. Meanwhile, we also establish the direct approximation theorem by Bernstein-Durrmeyer operators in $ L_{\rho _X }^2 $ with Borel probability measure.展开更多
Semi-supervised learning has been of growing interest over the past few years and many methods have been proposed. Although various algorithms are provided to implement semi-supervised learning,there are still gaps in...Semi-supervised learning has been of growing interest over the past few years and many methods have been proposed. Although various algorithms are provided to implement semi-supervised learning,there are still gaps in our understanding of the dependence of generalization error on the numbers of labeled and unlabeled data. In this paper,we consider a graph-based semi-supervised classification algorithm and establish its generalization error bounds. Our results show the close relations between the generalization performance and the structural invariants of data graph.展开更多
文摘This paper presents learning rates for the least-square regularized regression algorithms with polynomial kernels. The target is the error analysis for the regression problem in learning theory. A regularization scheme is given, which yields sharp learning rates. The rates depend on the dimension of polynomial space and polynomial reproducing kernel Hilbert space measured by covering numbers. Meanwhile, we also establish the direct approximation theorem by Bernstein-Durrmeyer operators in $ L_{\rho _X }^2 $ with Borel probability measure.
基金supported by National Natural Science Foundation of China (Grant No. 10771053)Specialized Research Foundation for the Doctoral Program of Higher Education of China (SRFDP) (Grant No. 20060512001)Natural Science Foundation of Hubei Province (Grant No. 2007ABA139)
文摘Semi-supervised learning has been of growing interest over the past few years and many methods have been proposed. Although various algorithms are provided to implement semi-supervised learning,there are still gaps in our understanding of the dependence of generalization error on the numbers of labeled and unlabeled data. In this paper,we consider a graph-based semi-supervised classification algorithm and establish its generalization error bounds. Our results show the close relations between the generalization performance and the structural invariants of data graph.
