ジャーナル論文 / Journal
- Iwata, S., Oki, T., and Sakaue, S., "Rate constant matrix contraction method for stiff master equations with detailed balance", SIAM J. Sci. Comput. 48(1), a261–a285, (2026).
- Soma, T., Tung, K. C., and Yoshida, Y., "Online Algorithms for Spectral Hypergraph Sparsification", Math. Program., 1–24, (2025).
- Riou, C., Honda, J., and Sugiyam, M., "The Survival Bandit Problem", Transactions on Machine Learning Rese, 1–66, (2024).
- Komiyama, J., and Noda, S., "On statistical discrimination as a failure of social learning: A multiarmed bandit approach", Manage. Sci., (2024).
- Komiyama, J., Fouché, E., and Honda, J., "Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits", J. Mach. Learn. Res. 25(112), 1–56, (2024).
- Komiyama, J., Ariu, K., Kato, M., and Qin, C., "Rate-Optimal Bayesian Simple Regret in Best Arm Identification", Math. Oper. Res. 49(3), 1629–1646, (2024).
- Kato, M., and Ito, S., "Best-of-Both-Worlds Linear Contextual Bandits", Transactions on Machine Learning Research, (2024).
- Kamijima, T., and Ito, S., "Contaminated Online Convex Optimization", Transactions on Machine Learning Research, (2024).
- Hara, S., Matsuura, M., Honda, J., and Ito, S., "Active model selection: A variance minimization approach", Mach. Learn. 113(11), 8327–8345, (2024).
国際会議 / Proceedings
- Mahara, R., Mizutani, R., Oki, T., and Yokoyama, T., "Position fair mechanisms allocating indivisible goods", Proceedings of the 40th Annual AAAI Conference on Artificial Intelligence (AAAI '26) 40(20), 17137–17144, (2026).
- Tsuchiya, T., Ito, S., and Luo, H., "Corrupted Learning Dynamics in Games", Proceedings of Thirty Eighth Conference on Learning Theory (COLT 2025), (2025).
- Sakaue, S., Bao, H., and Tsuchiya, T., "Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis", Proceedings of The 28th International Conference on Artificial Intelligence and Statistics 258, 46–54, (2025).
- Sakaue , S., and Oki, T., "Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming", Advances in Neural Information Processing Systems 37 (NeurIPS 2024), (2025).
- Raveh, O., Honda, J., and Sugiyama, M., "Multi-player approaches for dueling bandits", Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, PMLR 258, 1540–1548, (2025).
- Osogami, T., Honda, J., and Komiyama, J., "Optimal Estimation of the Best Mean in Multi-Armed Bandits", Advances in Neural Information Processing Systems, (2025).
- Oki, T., and Sakaue, S., "No-Regret M♮-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting", Advances in Neural Information Processing Systems 37 (NeurIPS 2024), (2025).
- Nguyen, Q., Ito, S., Komiyama , J., and Mehta, M., "Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching", Proceedings of Thirty Eighth Conference on Learning Theory (COLT 2025), (2025).
- Lee, J., Honda, J., Ito, S., and Oh, M., "Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems", Advances in Neural Information Processing Systems, (2025).
- Kimura, M., Kawashima, T., Soma, T., and Hino, H., "Difference-of-submodular Bregman Divergence.", Iclr, (2025).
- Jang, K., Komiyama, J., and Yamazaki, K., "Fixed Confidence Best Arm Identification in the Bayesian Setting", Advances in Neural Information Processing Systems 37 (NeurIPS 2024), (2025).
- Iwata, T., and Sakaue, S., "Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems", Proceedings of the 42nd International Conference on Machine Learning 267, 26627–26641, (2025).
- Iwamasa, Y., Oki, T., and Soma, T., "Algorithmic aspects of semistability of quiver representations", Proceedings of the 52nd International Colloquium on Automata, Languages and Programming (ICALP ’25), 99:1–99:18, (2025).
- Ito, S., Luo, H., Tsuchiya, T., and Wu, Y., "Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback", Proceedings of Thirty Eighth Conference on Learning Theory (COLT 2025), (2025).
- Ito, S., "On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice", Advances in Neural Information Processing Systems 37 (NeurIPS 2024), (2025).
- Garamvölgyi, D., Mizutani, R., Oki, T., Schwarcz, T., and Yamaguchi, Y., "Towards the proximity conjecture on group-labeled matroids", Proceedings of the 52nd International Colloquium on Automata, Languages and Programming (ICALP ’25), 85:1–85:17, (2025).
- Chen, B., Lee, J., and Honda, J., "Geometric Resampling in Nearly Linear Time for Follow-the-Perturbed-Leader with Best-of-Both-Worlds Guarantee in Bandit Problems", Proceedings of the 42nd International Conference on Machine Learning 267, 8403–8426, (2025).
- Chen, B., Ito, S., and Imaizumi, M., "Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning", Advances in Neural Information Processing Systems (NeurIPS2025), (2025).
- Bao, H., and Sakaue, S., "Inverse Optimization with Prediction Market: A Characterization of Scoring Rules for Elciting System States", Proceedings of The 28th International Conference on Artificial Intelligence and Statistics 258, 451–459, (2025).
- Azize, A., Wu, Y., Honda, J., Orabona, F., Ito, S., and Basu, D., "Optimal Regret of Bandits under Differential Privacy", Advances in Neural Information Processing Systems, (2025).
- Yokoyama, K., Ito, S., Matsuoka, T., Kimura, K., and Yokoo, M., "Online L♮-Convex Minimization", Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2024., 319–336, (2024).
- Yamada, H., Komiyama, J., Abe, K., and Iwasaki, A., "Learning fair division from bandit feedback", Aistats 2024 238, 3106–3114, (2024).
- Tsuchiya, T., and Ito, S., "Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets", Advances in Neural Information Processing Systems 37 (NeurIPS 2024) 37, 101671–101695, (2024).
- Tsuchiya, T., and Ito, S., "A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds", Advances in Neural Information Processing Systems 37 (NeurIPS 2024), (2024).
- Tsuchiya, T., Ito, S., and Honda, J., "Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring", The 41st International Conference on Machine Learning (ICML 2024) 235, 48768–48790, (2024).
- Shimizu, K., Honda, J., Ito, S., and Nakadai, S., "Learning with Posterior Sampling for Revenue Management under Time-varying Demand", Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 4911–4919, (2024).
- Lee, J., Honda, J., Ito, S., and Min-hwan, O., "Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds", The 37th Annual Conference on Learning Theory (COLT 2024) 247, 3375–3430, (2024).
- Ito, S., Tsuchiya, T., and Honda, J., "Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Ratio Analysis and Best-of-Both-Worlds", The 37th Annual Conference on Learning Theory (COLT 2024) 247, 2522–2563, (2024).
- Ichikawa, K., Ito, S., Hatano, D., Sumita, H., Fukunaga, T., Kakimura, N., and Kawarabayashi, K., "New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem", Proceedings of the AAAI Conference on Artificial Intelligence 38(11), 12708–12716, (2024).
- Tsuchiya, T., Ito, S., and Honda, J., "Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds", Advances in Neural Information Processing Systems 36, 47406–47437, (2023).
- Lee, J., Honda, J., and Sugiyama, M., "Thompson exploration with best challenger rule in best arm identification", Proceedings of the 15th Asian Conference on Machine Learning (ACML2023), 646–661, (2023).
- Komiyama, J., and Imaizumi, M., "High-dimensional Contextual Bandit Problem without Sparsity", Advances in Neural Information Processing Systems, (2023).
- Ito, S., and Takemura, K., "An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits.", Advances in Neural Information Processing Systems 36, 71582–71602, (2023).
- Ito, S., Hatano, D., Sumita, H., Takemura, K., Fukunaga, T., Kakimura, N., and Kawarabayashi, K., "Bandit Task Assignment with Unknown Processing Time.", Advances in Neural Information Processing Systems Curran Associates, Inc. 36, 8937–8957, (2023).

