Analysis of complex and high dimensional data via sparse regularization techniques
| Project/Area Number |
15K15946
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Statistical science
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
|
|---|
| Keywords | 高次元データ / スパース正則化 / ロバスト推測 / グラフィカルモデル / スパース推定 / ロバスト推定 |
|---|
| Outline of Final Research Achievements |
Some researches on complex and high dimensional data have been conducted via sparse regularization techniques. This research particularly focuses on dealing with outliers and exploiting a group structure. On the former case, robust and sparse linear regression analyses have been proposed when responses may be corrupted. An estimation technique of conditional independences among large dimensional variables also has been proposed under cell-wise corruption of data matrix. On the latter case, a simultaneous detection method of both covariates that entirely and partially affect responses has been proposed in the context of stratified linear regression.
|
Report
(4 results)
Research Products
(9 results)
