About

Supervisor

プロフィール写真:松島慎

Shin Matsushima ( 松島 慎 )

Associate Professor

Center for Education and Research in Information Science and Technology (CERIST), The University of Tokyo

Research theme Publications resume

Work and Education

2008. B.E., Department of Materials Engineering, Faculty of Engineering, The University of Tokyo
2010.  Master of Information Science and Technology, Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
2011. JSPS fellow(DC2)
2011. Department of Statistics, Purdue University, Visiting scholar
2013. Ph.D. (Information Science and Technology), Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
2013. JSPS fellow(PD)
2013. Assistant Professor, Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
2018. Full-time Lecturer, Department of General Systems Studies, Graduate School of Arts and Sciences, The University of Tokyo
2020. Current position

Master Student

Takuto Kimura (Department of Creative Informatics, Graduate School of Information Science and Technology)

Ziyu Guo (Department of Creative Informatics, Graduate School of Information Science and Technology)
Hiroki Nishimoto (Department of General Systems Studies, Graduate School of Arts of Sciences)
Hiroya Iyori (Department of Creative Informatics, Graduate School of Information Science and Technology)

Bachelor Student

Kota Misaki (Department of  Interdisciplinary Science, College of Arts and Sciences)

Alumni

Masaki Kozuki (Department of General Systems Studies, Graduate School of Arts of Sciences)
Shota Hayashi (Department of General Systems Studies, Graduate School of Arts of Sciences)

Master and PhD positions

Our laboratory focuses on both the practical application and fundamental theory of machine learning.
Our key approach is to develop efficient algorithms that can easily be used by anybody.
As for research into the theory, we evaluate statistical properties of machine learning methods and the efficiency of learning algorithms.
We do this via statistical learning and optimization theory with a view towards developing methods that guarantee favorable behaviors in the real world.
As for research into the applications, we develop methods and algorithms tailored to the properties and structure of real world data with the goal of knowledge discovery and value creation.

keywords: learning theory / convex optimization / knowledge discovery / large-scale learning / sparse learning / asynchronous optimization / generalized additive models / subspace clustering

One can join our group as a student at the department of creative informatics in the graduate school of information science and technology or the department of general systems studies in the graduate school of arts and sciences; information for the application can be found  here (IST) and here (AS).
Please feel free to contact us through the contact form for lab viewing, possible research topics, personal career plans, etc.