spacer


Junya Honda / Lecturer / Division of Transdisciplinary Sciences
Department of Complexity Science / / Machine learning, Information theory
http://www.ms.k.u-tokyo.ac.jp/honda/index.html

Career Summary
2008: Graduated from Faculty of Engineering (University of Tokyo)
2013: Received Ph.D. in science (University of Tokyo)
2013.4-2016.12: Research associate (University of Tokyo)
2017.1-present: Lecturer (University of Tokyo)

Educational Activities
Statistical Machine Learning, Advanced Data Analysis, Intelligent Systems
Research Activities
We research the theory and application of decision making in machine learning. We are particularly interested in the bandit problems that are widely seen in advertisement and investment.

Literature
1) Junya Honda and Akimichi Takemura: Non-Asymptotic Analysis of a New Bandit Algorithm for Semi-Bounded Rewards. Journal of Machine Learning Research, vol.16, pp.1721-3756, 2015.

Other Activities
Institute of Electrical and Electronics Engineers (IEEE)
Institute of Electronics, Information and Communication Engineers of Japan (IEICE)
spacer
Future Plan
Our objective is to contribute to scientific discovery by the development of generic decision-making theory to avoid trial and error.
Messages to Students
In the area of machine learning we face totally different problems depending on how we collect the data and what aspect we focus on. I hope students will challenge themselves to tackle these problems from diverse viewpoints and ideas.

top