RIKEN Center for Advanced Intelligence Project Computational Learning Theory Team
Team Director: Kohei Hatano (D.Sc.)
Research Summary

We try to formulate and solve various problems in machine learning from a theoretical computer science perspective. One of our primary research topics is online decision making problems, where the (possibly adversarial) environment and the player interact iteratively. Our goal is to clarify the limits of the player’s strategies for various online decision problems under continuous/discrete constraints and to develop robust and efficient strategies based on theoretical analyses. We also keep connections with other different areas and investigate new applications of machine learning techniques.
Research Subjects:
- Online Prediction
- Machine Learning
- Applications of machine learning to other disciplines
Main Research Fields
- Computer Science
Selected Publications
- 1.
Sherief Hashima, Zubair Md. Fadlullah, Mostafa M. Fouda, Kohei Hatano, Eiji Takimoto, Mohsen Guizani:
"A Dual-Objective Bandit-Based Opportunistic Band Selection Strategy for Hybrid-Band V2X Metaverse Content Update."
GLOBECOM 2023: 6880-6885 - 2.
Yiping Tang, Kohei Hatano, Eiji Takimoto:
"Boosting-Based Construction of BDDs for Linear Threshold Functions and Its Application to Verification of Neural Networks."
DS 2023: 477-491 - 3.
Yuta Kurokawa, Ryotaro Mitsuboshi, Haruki Hamasaki, Kohei Hatano, Eiji Takimoto, Holakou Rahmanian:
"Extended Formulations via Decision Diagrams."
COCOON (2) 2023: 17-28 - 4.
Daiki Suehiro, Eiji Takimoto:
"Simplified and Unified Analysis of Various Learning Problems by Reduction to Multiple-Instance Learning"
Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022), 2022.8, PMLR 180:1896-1906. - 5.
Yaxiong Liu, Kohei Hatano, Eiji Takimoto:
"Improved Algorithms for Online Load Balancing."
SOFSEM 2021: 203-217 - 6.
Sherief Hashima, Mostafa M. Fouda, Zubair Md. Fadlullah, Ehab Mahmoud Mohamed, Kohei Hatano:
"Improved UCB-based Energy-Efficient Channel Selection in Hybrid-Band Wireless Communication."
GLOBECOM 2021: 1-6 - 7.
Daiki Suehiro, Kohei Hatano, Eiji Takimoto, Shuji Yamamoto, Kenichi Bannai, Akiko Takeda:
"Theory and Algorithms for Shapelet-Based Multiple-Instance Learning."
Neural Comput. 32(8): 1580-1613 (2020) - 8.
Sherief Hashima, Kohei Hatano, Eiji Takimoto, Ehab Mahmoud Mohamed:
"Neighbor Discovery and Selection in Millimeter Wave D2D Networks Using Stochastic MAB."
IEEE Commun. Lett. 24(8): 1840-1844 (2020) - 9.
Takahiro Fujita, Kohei Hatano, Eiji Takimoto:
"Boosting over non-deterministic ZDDs."
Theor. Comput. Sci. 806: 81-89 (2020)
Related Links
Lab Members
Principal investigator
- Kohei Hatano
- Team Director
Core members
- Sherief Mostafa Salman Hashima
- Research Scientist
- Daiki Suehiro
- Visiting Scientist
- Xuanke Jiang
- Research Part-time Worker I
- Shang Lu
- Research Part-time Worker I
Contact Information
Faculty of Arts and Science, Kyushu University
744 Motooka Nishi-ku Fukuoka, Japan
Email: kohei.hatano@riken.jp