On the Convergence Rate of Kernel-Based Sequential Greedy Regression
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 ra...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2012-01-01
|
| Series: | Abstract and Applied Analysis |
| Online Access: | http://dx.doi.org/10.1155/2012/619138 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832562169047154688 |
|---|---|
| author | Xiaoyin Wang Xiaoyan Wei Zhibin Pan |
| author_facet | Xiaoyin Wang Xiaoyan Wei Zhibin Pan |
| author_sort | Xiaoyin Wang |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-1f17ff9796564d349bf3aca856ecd294 |
| institution | Kabale University |
| issn | 1085-3375 1687-0409 |
| language | English |
| publishDate | 2012-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Abstract and Applied Analysis |
| spelling | doaj-art-1f17ff9796564d349bf3aca856ecd2942025-02-03T01:23:15ZengWileyAbstract and Applied Analysis1085-33751687-04092012-01-01201210.1155/2012/619138619138On the Convergence Rate of Kernel-Based Sequential Greedy RegressionXiaoyin Wang0Xiaoyan Wei1Zhibin Pan2College of Sciences, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Statistics and Applied Mathematics, Hubei University of Economics, Wuhan 430205, ChinaCollege of Sciences, Huazhong Agricultural University, Wuhan 430070, ChinaA 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.http://dx.doi.org/10.1155/2012/619138 |
| spellingShingle | Xiaoyin Wang Xiaoyan Wei Zhibin Pan On the Convergence Rate of Kernel-Based Sequential Greedy Regression Abstract and Applied Analysis |
| title | On the Convergence Rate of Kernel-Based Sequential Greedy Regression |
| title_full | On the Convergence Rate of Kernel-Based Sequential Greedy Regression |
| title_fullStr | On the Convergence Rate of Kernel-Based Sequential Greedy Regression |
| title_full_unstemmed | On the Convergence Rate of Kernel-Based Sequential Greedy Regression |
| title_short | On the Convergence Rate of Kernel-Based Sequential Greedy Regression |
| title_sort | on the convergence rate of kernel based sequential greedy regression |
| url | http://dx.doi.org/10.1155/2012/619138 |
| work_keys_str_mv | AT xiaoyinwang ontheconvergencerateofkernelbasedsequentialgreedyregression AT xiaoyanwei ontheconvergencerateofkernelbasedsequentialgreedyregression AT zhibinpan ontheconvergencerateofkernelbasedsequentialgreedyregression |