On the Convergence Rate of Kernel-Based Sequential Greedy Regression | Zendy

Xiaoyin Wang | Zendy; Xiaoyan Wei | Zendy; Zhibin Pan | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

On the Convergence Rate of Kernel-Based Sequential Greedy Regression

Author(s) -

Xiaoyin Wang,

Xiaoyan Wei,

Zhibin Pan

Publication year - 2012

Publication title -

abstract and applied analysis

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.228

H-Index - 56

eISSN - 1687-0409

pISSN - 1085-3375

DOI - 10.1155/2012/619138

Subject(s) - mathematics , generalization , measure (data warehouse) , rate of convergence , kernel (algebra) , greedy algorithm , convergence (economics) , basis (linear algebra) , upper and lower bounds , mathematical optimization , combinatorics , mathematical analysis , computer science , data mining , computer network , channel (broadcasting) , geometry , economics , economic growth

A kernel-based greedy algorithm is presented to realize efficient sparse learning with data-dependent basis functions. Upper bound of generalization error is obtained based on complexity measure of hypothesis space with covering numbers. A careful analysis shows the error has a satisfactory decay rate under mild conditions

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research