Study of prediction theory based on game-theoretic probability
Project/Area Number |
22650057
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Single-year Grants |
Research Field |
Statistical science
|
Research Institution | The University of Tokyo |
Principal Investigator |
TAKEMURA Akimichi 東京大学, 大学院・情報理工学系研究科, 教授 (10171670)
|
Project Period (FY) |
2010 – 2012
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥3,340,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2011: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2010: ¥1,000,000 (Direct Cost: ¥1,000,000)
|
Keywords | 統計的予測・制御 / ゲーム論的確率論 / 確率予測 / 重複対数の法則 / ロジスティック回帰 / 多変量解析 / 分類・パタン認識 / 計算機集約的統計 / 大数法則 / 中心極限定理 / マルチンゲール / 数理ファイナンス |
Research Abstract |
The game-theoretic probability initiated by Shafer and Vovk reconstructs the probability theory based only on protocols of games. In this study we obtained many results in this framework, such as reconstruction of pricing theory in multinomial games, probability forecasting based on regression, and new sufficient condition for the law of iterated logarithm.
|
Report
(4 results)
Research Products
(29 results)