Theory and Application of Information-Based Machine Learning
Project/Area Number |
25700022
|
Research Category |
Grant-in-Aid for Young Scientists (A)
|
Allocation Type | Partial Multi-year Fund |
Research Field |
Intelligent informatics
|
Research Institution | The University of Tokyo (2014-2016) Tokyo Institute of Technology (2013) |
Principal Investigator |
|
Project Period (FY) |
2013-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥25,350,000 (Direct Cost: ¥19,500,000、Indirect Cost: ¥5,850,000)
Fiscal Year 2016: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2015: ¥7,930,000 (Direct Cost: ¥6,100,000、Indirect Cost: ¥1,830,000)
Fiscal Year 2014: ¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2013: ¥8,320,000 (Direct Cost: ¥6,400,000、Indirect Cost: ¥1,920,000)
|
Keywords | 機械学習 / 情報量 / 密度比 / 密度差 / 密度微分 / 教師付き学習 / 教師なし学習 / 強化学習 / クラス事前確率推定 / 次元削減 / リーマン幾何 / 類似度 / ダイバージェンス / 密度差推定 |
Outline of Final Research Achievements |
In this research project, we developed methods for directly learning the density ratio and density difference without estimating each density, and based on them, we developed various machine learning algorithms. This includes algorithms of semi-supervised classification, unsupervised clustering, supervised causal inference, supervised dimension reduction, unsupervised dimension reduction, classification from positive and unlabeled data, supervised learning under target shift, and cross-domain object matching. We also developed methods for directly learning the density derivative without estimating the density itself, and based on them, we developed algorithms of modal regression and non-Gaussian component analysis.
|
Report
(5 results)
Research Products
(46 results)
-
-
-
-
-
-
-
-
-
-
-
-
[Journal Article] Cross-domain matching with squared-loss mutual information2015
Author(s)
Yamada, M., Sigal, L., Raptis, M., Toyoda, M., Chang, Y., & Sugiyama, M.
-
Journal Title
IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume: 37
Pages: 1764-1776
Related Report
Peer Reviewed / Acknowledgement Compliant
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Policy search with high-dimensional context variables2017
Author(s)
Tangkaratt, V., van Hoof, H., Parisi, S., Neumann, G., Peters, J., & Sugiyama, M.
Organizer
Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI2017)
Place of Presentation
San Francisco, California, USA
Year and Date
2017-02-04
Related Report
Int'l Joint Research
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Bias reduction and metric learning for nearest-neighbor estimation of Kullback-Leibler divergence.2014
Author(s)
Noh, Y.-K., Sugiyama, M., Liu, S., du Plessis, M. C., Park, F. C., & Lee, D. D.
Organizer
International Conference on Artificial Intelligence and Statistics (AISTATS2014)
Place of Presentation
Reykjavik, Iceland
Year and Date
2014-04-22 – 2014-04-24
Related Report
-
[Presentation] Squared-loss mutual information regularization.2013
Author(s)
Niu, G., Jitkrittum, W., Dai, B., Hachiya, H., & Sugiyama, M.
Organizer
30th International Conference on Machine Learning (ICML2013)
Place of Presentation
Atlanta, Georgia, USA
Related Report
-
-
-
-
-
-
-
-