Abstract and Applied Analysis (Jan 2012)

On the Convergence Rate of Kernel-Based Sequential Greedy Regression

  • Xiaoyin Wang,
  • Xiaoyan Wei,
  • Zhibin Pan

DOI
https://doi.org/10.1155/2012/619138
Journal volume & issue
Vol. 2012

Abstract

Read online

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.