2010 Fiscal Year Final Research Report
Efficient Learning of Maximum Margin Sparse Hyperplanes wih Bias
| Project/Area Number |
21700171
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
HATANO Kohei Kyushu University, システム情報科学研究院, 助教 (60404026)
|
|---|
| Project Period (FY) |
2009 – 2010
|
| Keywords | 機械学習 / 計算学習理論 / オンライン予測 / ブースティング / ソフトマージン最適化 / サポートベクターマシン |
|---|
| Research Abstract |
The 1-norm soft margin optimization is a popular formulation for obtaining sparse classifiers. We propose a new boosting algorithm based on linear programming. Our algorithm can take advantage of the sparsity of the solution of the underlying optimization problem. In preliminary experiments, our algorithm outperforms a state-of-the-art LP solver and LPBoost.
|
