Online Decision Making by Convex Optimization
| Project/Area Number |
23300003
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Fundamental theory of informatics
|
|---|
| Research Institution | Kyushu University |
|---|
Principal Investigator |
TAKIMOTO Eiji 九州大学, システム情報科学研究科(研究院, 教授 (50236395)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
HATANO Kohei 九州大学, システム情報科学研究院, 助教 (60404026)
|
|---|
| Project Period (FY) |
2011-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥14,300,000 (Direct Cost: ¥11,000,000、Indirect Cost: ¥3,300,000)
Fiscal Year 2014: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2013: ¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2012: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2011: ¥5,460,000 (Direct Cost: ¥4,200,000、Indirect Cost: ¥1,260,000)
|
|---|
| Keywords | 計算学習理論 / オンライン予測 / 凸最適化 / 組合せ最適化 / オンラインアルゴリズム / 凸最適化理論 / バンディット問題 / 競合比解析 / LP緩和 / 近似アルゴリズム / モンテカルロ木探索 / ２部ランキング学習 / 劣モジュラ最適化 / 基多面体 / 線形分類器学習 / Bradley-Terryモデル / ランキング学習 |
|---|
| Outline of Final Research Achievements |
Online decision making is a process where decision making and data observation are repeated. It is widely recognized that, for various problems of decision making, convex optimization theory gives a general framework of design and analysis of algorithms. However, it is limited to those problems where the domains or the decision spaces are continuous. In this study, we extend the theory so that it can be uniformly applied to a wide class of discrete domains such as rankings, spanning trees and a set of satisfying assignments. Furthermore, we consider a generalized problem where the cost of decision making for each trial depends on the past decisions made so far, and give a condition under which the problem has an efficient and high performing algorithm.
|
Report
(5 results)
Research Products
(59 results)
-
-
[Journal Article] Bandit online optimization over permutahedron2014
Author(s)
Nir Ailon, Kohei Hatano, Eiji Takimoto
-
Journal Title
Proc. 25th International Conference on Algorithmic Learning Theory (ALT 2014), Lecture Notes in Artificial Ingtelligence
Volume: 8776
Pages: 215-229
DOI
ISBN
9783319116617, 9783319116624
Related Report
Peer Reviewed / Acknowledgement Compliant
-
-
-
-
-
-
[Journal Article] Combinatorial Online Prediction via Metarounding2013
Author(s)
Takahiro Fujita, Kohei Hatano, Eiji Takimoto
-
Journal Title
Proc. 24th International Conference on Algorithmic Learning Theory (ALT 2013), Lecture Notes in Artificial Intelligence
Volume: 8139
Pages: 68-82
DOI
NAID
ISBN
9783642409349, 9783642409356
Related Report
Peer Reviewed
-
-
[Journal Article] Online Rank Aggregation2012
Author(s)
Shota Yasutake
-
Journal Title
Proc. 4th Conference on Asian Conference on Machine Learning, JMLR Workshop and Conference Proceedings
Volume: 25
Related Report
Peer Reviewed
-
-
-
-
-
-
-
-
[Presentation] Online prediction with Bradley-Terry models2014
Author(s)
Issei Matsumoto, Kohei Hatano, Eiji Takimoto
Organizer
NIPS 2014 Workshop on Analysis of Rank Data: Confluence of Social Choice, Operations Research, and Machine Learning
Place of Presentation
Montreal (Canada)
Year and Date
2014-12-13
Related Report
-
-
-
-
-
-
-
[Presentation] オンライン凸最適化2014
Author(s)
瀧本英二
Organizer
京都大学数理解析研究所「組合せ最適化セミナー」
Place of Presentation
京都大学（京都府京都市）
Year and Date
2014-08-01
Related Report
Invited
-
-
-
-
-
[Presentation] Online Rank Aggregation2011
Author(s)
Shota Yasutake
Organizer
NIPS 2011 Workshop on Computational Trade-offs in Statistical Learning (COST)
Place of Presentation
Sierra Nevada Ski Resort, Spain
Year and Date
2011-12-16
Related Report
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
