Construction and evaluation of non-Gaussian spatio-temporal models through the use of gradient maps
Project/Area Number |
19700258
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Single-year Grants |
Research Field |
Statistical science
|
Research Institution | The University of Tokyo |
Principal Investigator |
SEI Tomonari The University of Tokyo, 大学院・情報理工学系研究科, 助教 (20401242)
|
Project Period (FY) |
2007 – 2010
|
Project Status |
Completed (Fiscal Year 2010)
|
Budget Amount *help |
¥3,920,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥720,000)
Fiscal Year 2010: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2009: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2008: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2007: ¥800,000 (Direct Cost: ¥800,000)
|
Keywords | 勾配写像 / 凸最適化問題 / 輸送問題 / 方向統計学 / 時空間モデル / 凸関数 / 非ガウスモデル / グラフィカルモデリング / 多変量解析 / 不等分散性 |
Research Abstract |
For data in the form of function of time and space, we proposed a statistical model to extract complex structures behind the data. We used the gradient map as a special transformation. In particular, we apply a sparse estimation method, which is an analogy of recently developed methodology in machine learning theory. Furthermore, we generalize our models to those of directional data. We also clarify a theoretical merit of our models from the viewpoint of loss of estimation.
|
Report
(6 results)
Research Products
(35 results)