Project/Area Number |
26820174
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Control engineering/System engineering
|
Research Institution | Tokyo Metropolitan Industrial Technology Research Institute |
Principal Investigator |
Kaneda Yasuaki 地方独立行政法人東京都立産業技術研究センター, 開発本部開発第一部情報技術グループ, 主任研究員 (20463010)
|
Project Period (FY) |
2014-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2015: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2014: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
|
Keywords | スパース推定 / L1正則化 / 正則化パラメータ / 逐次アルゴリズム / 機械学習 |
Outline of Final Research Achievements |
For L1 regularized linear regression problem, we show that a regularization parameter of the problem is related to a second moment of measurement noise and propose a systematic design method of the parameter using the relation. Moreover, we derive an approximated solution of the problem, which can be solved analytically and recursively. Numerical simulations demonstrate effectiveness of the proposed methods.
|