On the Convergence Rate of Kernel‐Based Sequential Greedy Regression
Xiaoyin Wang, Xiaoyan Wei, Zhibin Pan · Abstract and Applied Analysis · 2012
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.