I am a senior lecturer at Kyoto University.
Previously, I was an assistant professor at National Institute of Informatics and SOKENDAI.
I received my PhD from University of Tokyo in 2020, where I was advised by Prof. Satoru Iwata.
Office: Yoshida Campus, Research Building No.7, Room 328
Email: fujii+at+i.kyoto-u.ac.jp
dblp google scholar
Research Interests
My research interests lie in the intersection of combinatorial optimization, machine learning, and game theory.I am particularly interested in submodular maximization, active learning, optimal stopping theory, online learning, and correlated equilibria.
Opportunities
I am looking for prospective students for the Master’s and PhD programs in the Graduate School of Informatics at Kyoto University who are interested in optimization, machine learning, and/or game theory.If you are interested, please do not hesitate to contact me via email. Please refer to these slides, these slides, or these slides for more information about my research area.
I also welcome visitors, research interns, and postdocs; if you require financial support, please contact me to discuss possible options.
Interns (at NII): Mohamed Ouaguenouni (Sorbonne Université, 2025/06 - 2025/08), Max Dupré la Tour (McGill University, 2025/04 - 2025/07), Orane Belhomme (École normale supérieure de Lyon, 2025/04 - 2025/07), Bastian Schnitzer (University of Freiburg, 2025/01 - 2025/04)
Refereed Publications
- Yi Feng, Kaito Fujii, Stratis Skoulakis, Xiao Wang, and Volkan Cevher (the first four authors are ordered alphabetically)
Continuous-time analysis of heavy ball momentum in min-max games
Proceedings of the 42nd International Conference on Machine Learning (ICML 2025), pp. 16670--16710, 2025. - Kaito Fujii
The power of mediators: Price of anarchy and stability in Bayesian games with submodular social welfare
(Previous title: Power of mediators in Bayesian games with submodular social welfare)
Proceedings of the 26th ACM Conference on Economics and Computation (EC 2025), pp. 251--251, 2025.
[slides] [slides (60 min. at UTokyo)] - Kaito Fujii
Bayes correlated equilibria, no-regret dynamics in Bayesian games, and the price of anarchy
(Previous title: Bayes correlated equilibria and no-regret dynamics)
Proceedings of the 38th Conference on Learning Theory (COLT 2025), pp. 2190--2191, 2025.
[slides] [slides (30 min. at RIKEN)] - M. Kozai, Y. Hayashi, K. Fujii, K. Munakata, C. Kato, N. Miyashita, A. Kadokura, R. Kataoka, S. Miyake, M.L. Duldig, J.E. Humble, K. Iwai
Cosmic ray north-south anisotropy: rigidity spectrum and solar cycle variations observed by ground-based muon detectors
The Astrophysical Journal, 977(2), 160, 2024. - Kaito Fujii and Yuichi Yoshida (alphabetical order)
The secretary problem with predictions
Mathematics of Operations Research, 49(2), pp. 1241--1262, 2023. - Shinichi Hemmi, Taihei Oki, Shinsaku Sakaue, Kaito Fujii, and Satoru Iwata
Lazy and fast greedy MAP inference for determinantal point process
Advances in Neural Information Processing Systems (NeurIPS 2022), 35, pp. 2776--2789, 2022.
- Thi Ha Ly Dinh, Megumi Kaneko, and Kaito Fujii
Device selection and beamforming optimization in large-scale mmWave IoT networks
IEEE Internet of Things Journal, 9(24), pp. 25395--25408, 2022.
- Tomohiro Nakamura, Shinsaku Sakaue, Kaito Fujii, Yu Harabuchi, Satoshi Maeda, and Satoru Iwata
Selecting molecules with diverse structures and properties by maximizing submodular functions of descriptors learned with graph neural networks
Scientific Reports, 12, 1124, 2022. - Kaito Fujii and Shinsaku Sakaue (alphabetical order)
Algorithmic Bayesian persuasion with combinatorial actions
Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI 2022), 36(5), pp. 5016--5024, 2022.
[slides] - Kaito Fujii, Tasuku Soma, and Yuichi Yoshida (alphabetical order)
Polynomial-time algorithms for submodular Laplacian systems
Theoretical Computer Science, 892(12), pp. 170--186, 2021. - Kaito Fujii
Approximation guarantees of local search algorithms via localizability of set functions
Proceedings of the 37th International Conference on Machine Learning (ICML 2020), pp. 3327--3336, 2020.
[slides] - Kaito Fujii and Shinsaku Sakaue
Beyond adaptive submodularity: Approximation guarantees of greedy policy with adaptive submodularity ratio
Proceedings of the 36th International Conference on Machine Learning (ICML 2019), pp. 2042--2051, 2019.
[poster] [slides] - Kaito Fujii and Tasuku Soma (alphabetical order)
Fast greedy algorithms for dictionary selection with generalized sparsity constraints
Advances in Neural Information Processing Systems (NeurIPS 2018), 31, pp. 4745--4754, 2018. Spotlight (top 4% submissions).
[poster] [spotlight slides] - Kaito Fujii and Hisashi Kashima
Budgeted stream-based active learning via adaptive submodular maximization
Advances in Neural Information Processing Systems (NIPS 2016), 29, pp. 514--522, 2016. - Kaito Fujii
Faster approximation algorithms for maximizing a monotone submodular function subject to a b-matching constraint
Information Processing Letters, 116(9), pp. 578--584, 2016.
Preprints
- Max Dupré la Tour and Kaito Fujii
Discrepancy and fair division for non-additive valuations
ArXiv preprints, 2025. - Kaito Fujii
An improved algorithm for the submodular secretary problem with a cardinality constraint
ArXiv preprints, 2019.