This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers.A comparison relationship b...This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers.A comparison relationship between the excess misclassification error and the excess generalization error is provided;from this,along with the convex analysis theory,a kind of learning rate is derived.The results show that the performance of the classifier is effected by the outliers,and the extent of impact can be controlled by choosing the homotopy parameters properly.展开更多
The properties of generalized convexity are studied in this paper,as well as an existence Theorem of solutions for a type of generalized quasi-variational inequality is then abtained.
In this paper,we present an analysis about the rate of convergence of an inexact proximal point algorithm to solve minimization problems for quasiconvex objective functions on Hadamard manifolds.We prove that under na...In this paper,we present an analysis about the rate of convergence of an inexact proximal point algorithm to solve minimization problems for quasiconvex objective functions on Hadamard manifolds.We prove that under natural assumptions the sequence generated by the algorithm converges linearly or superlinearly to a critical point of the problem.展开更多
In this paper we present two inexact proximal point algorithms to solve minimization problems for quasiconvex objective functions on Hadamard manifolds.We prove that under natural assumptions the sequence generated by...In this paper we present two inexact proximal point algorithms to solve minimization problems for quasiconvex objective functions on Hadamard manifolds.We prove that under natural assumptions the sequence generated by the algorithms are well defined and converge to critical points of the problem.We also present an application of the method to demand theory in economy.展开更多
In this paper, we investigate the connectedness of G-proper efficient solution set for multiobjective programming problem. It is shown that the G-proper efficient solution set is connected if objective functions are c...In this paper, we investigate the connectedness of G-proper efficient solution set for multiobjective programming problem. It is shown that the G-proper efficient solution set is connected if objective functions are convex. A sufficient condition for the connectedness of G-proper efficient solution set is established when objective functions are strictly quasiconvex.展开更多
基金supported by the NSF(61877039)the NSFC/RGC Joint Research Scheme(12061160462 and N City U 102/20)of China+2 种基金the NSF(LY19F020013)of Zhejiang Provincethe Special Project for Scientific and Technological Cooperation(20212BDH80021)of Jiangxi Provincethe Science and Technology Project in Jiangxi Province Department of Education(GJJ211334)。
文摘This paper considers a robust kernel regularized classification algorithm with a non-convex loss function which is proposed to alleviate the performance deterioration caused by the outliers.A comparison relationship between the excess misclassification error and the excess generalization error is provided;from this,along with the convex analysis theory,a kind of learning rate is derived.The results show that the performance of the classifier is effected by the outliers,and the extent of impact can be controlled by choosing the homotopy parameters properly.
文摘The properties of generalized convexity are studied in this paper,as well as an existence Theorem of solutions for a type of generalized quasi-variational inequality is then abtained.
基金Coordenação de Aperfeiçoamento de Pessoal de Nível Superior of the Federal University of Rio de Janeiro(UFRJ),Brazil.
文摘In this paper,we present an analysis about the rate of convergence of an inexact proximal point algorithm to solve minimization problems for quasiconvex objective functions on Hadamard manifolds.We prove that under natural assumptions the sequence generated by the algorithm converges linearly or superlinearly to a critical point of the problem.
文摘In this paper we present two inexact proximal point algorithms to solve minimization problems for quasiconvex objective functions on Hadamard manifolds.We prove that under natural assumptions the sequence generated by the algorithms are well defined and converge to critical points of the problem.We also present an application of the method to demand theory in economy.
基金This work is supported by Research Foundation of the Education Departm entof Zhejiang Province(2 0 0 10 2 80 )
文摘In this paper, we investigate the connectedness of G-proper efficient solution set for multiobjective programming problem. It is shown that the G-proper efficient solution set is connected if objective functions are convex. A sufficient condition for the connectedness of G-proper efficient solution set is established when objective functions are strictly quasiconvex.
