Kei KOBAYASHI
Assistant Professor, Mathematical Statistics Group, Department of Mathematical Analysis and Statistical Inference
Phone: +81-50-5533-8500
E-mail: kei
Date of Birth: May, 1977
Education: Bachelor of Engineering, Department of Mathematical Engineering and Instrumental Physics, University of Tokyo, 2000
Master of Engineering, Department of Mathematical Engineering and Instrumental Physics, University of Tokyo, 2002
Doctor of Information Science and Technology, Graduate School of Information Science and Technology, University of Tokyo, 2005
Degree: Doctor of Information Science and Technology, University of Tokyo, 2005, Title of the Thesis: Bayesian theory for kernel machines and network models.
Employment: 2002.4-2005.3  JSPS Research Fellowships for Doctor Course Student
2005.4-2007.7  JSPS Research Fellowships for Postdoctoral Fellows
2005.11-2007.4 Postdoctoral fellow, Department of Statistics, University of California, Berkeley
2007.8-  Assistant Professor, Mathematical Statistics Group, Department of Mathematical Analysis and Statistical Inference
Research
Fields:
Statistical learning theory, Model selection and prediction theory, Network models.
Research
Themes:
Information criteria for kernel machines, Risk-sensitive network decision problem, Bayesian shrinkage prediction for linear regression problem, Probability theory for ranking problem in a tournament


Selected Papers
(1) Kobayashi, K. and Sugihara, K. (2002), Crystal Voronoi diagram and its applications, Future Generation Computer System, 18, 681-692.
(2) Kobayashi, K. and Komaki, F. (2006), Information criteria for support vector machines, IEEE transactions on Neural Networks, 17 (3), 571-577.
(3) Kobayashi, K., Kawasaki, H. and Takemura, A. (2006), Parallel matching for ranking all teams in a tournament, Advances in Applied Probability, 38 (8), 804-826.
(4) Kobayashi, K. and Komaki, F. (2008), Bayesian shrinkage prediction for the regression problem, Journal of Multivariate Analysis, 99 (9), 1888-1905.

Membership of Academic Societies
Japan Statistical Society, Institute of Mathematical Statistics