Junpei Komiyama

56 papers A* 12A 3B 1C 1Journal 34Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	An Efficient Algorithm for Thresholding Monte Carlo Tree Search. CoRR Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama, Koji Tabata
2026	J	`jnl`	On Statistical Discrimination as a Failure of Social Learning: A Multiarmed Bandit Approach. Manag. Sci. Junpei Komiyama, Shunya Noda
2025	J	`jnl`	Best-of-∞ - Asymptotic Performance of Test-Time Compute. CoRR Junpei Komiyama, Daisuke Oba, Masafumi Oyamada
2025	J	`jnl`	Data-dependent Bounds with CoRR Quan Nguyen, Shinji Ito, Junpei Komiyama, Nishant A. Mehta
2025	A*	`conf`	Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching. COLT Quan M. Nguyen, Shinji Ito, Junpei Komiyama, Nishant A. Mehta
2025	J	`jnl`	High-dimensional Nonparametric Contextual Bandit Problem. CoRR Shogo Iwazaki, Junpei Komiyama, Masaaki Imaizumi
2025	A*	`conf`	No-Regret Incentive-Compatible Online Learning under Exact Truthfulness with Non-Myopic Experts. EC Junpei Komiyama, Nishant A. Mehta, Ali Mortazavi
2025	J	`jnl`	No-regret incentive-compatible online learning under exact truthfulness with non-myopic experts. CoRR Junpei Komiyama, Nishant A. Mehta, Ali Mortazavi
2025	J	`jnl`	Rate-optimal Design for Anytime Best Arm Identification. CoRR Junpei Komiyama, Kyoungseok Jang, Junya Honda
2024	J	`jnl`	Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits. J. Mach. Learn. Res. Junpei Komiyama, Edouard Fouché, Junya Honda
2024	A*	`conf`	Fixed Confidence Best Arm Identification in the Bayesian Setting. NeurIPS Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki
2024	J	`jnl`	Fixed Confidence Best Arm Identification in the Bayesian Setting. CoRR Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki
2024	A	`conf`	Learning Fair Division from Bandit Feedback. AISTATS Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki
2024	J	`jnl`	Rate-Optimal Bayesian Simple Regret in Best Arm Identification. Math. Oper. Res. Junpei Komiyama, Kaito Ariu, Masahiro Kato, Chao Qin
2024	J	`jnl`	Replicability is Asymptotically Free in Multi-armed Bandits. CoRR Junpei Komiyama, Shinji Ito, Yuichi Yoshida, Souta Koshino
2023	A*	`conf`	High-dimensional Contextual Bandit Problem without Sparsity. NeurIPS Junpei Komiyama, Masaaki Imaizumi
2023	J	`jnl`	High-dimensional Contextual Bandit Problem without Sparsity. CoRR Junpei Komiyama, Masaaki Imaizumi
2023	J	`jnl`	Learning Fair Division from Bandit Feedback. CoRR Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki
2023	A	`conf`	Posterior Tracking Algorithm for Classification Bandits. AISTATS Koji Tabata, Junpei Komiyama, Atsuyoshi Nakamura, Tamiki Komatsuzaki
2023	A	`conf`	Thresholded linear bandits. AISTATS Nishant A. Mehta, Junpei Komiyama, Vamsi K. Potluru, Andrea Nguyen, Mica Grant-Hagen
2022	A*	`conf`	Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search. IJCAI Kenshi Abe, Junpei Komiyama, Atsushi Iwasaki
2022	J	`jnl`	Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search. CoRR Kenshi Abe, Junpei Komiyama, Atsushi Iwasaki
2022	J	`jnl`	Bayes Optimal Algorithm is Suboptimal in Frequentist Best Arm Identification. CoRR Junpei Komiyama
2022	J	`jnl`	Bridging Offline and Online Experimentation: Constraint Active Search for Deployed Performance Optimization. Trans. Mach. Learn. Res. Junpei Komiyama, Gustavo Malkomes, Bolong Cheng, Michael McCourt
2022	J	`jnl`	Globally Optimal Algorithms for Fixed-Budget Best Arm Identification. CoRR Junpei Komiyama, Taira Tsuchiya, Junya Honda
2022	A*	`conf`	Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification. NeurIPS Junpei Komiyama, Taira Tsuchiya, Junya Honda
2022	J	`jnl`	Strategic Choices of Migrants and Smugglers in the Central Mediterranean Sea. CoRR Katherine Hoffmann Pham, Junpei Komiyama
2021	J	`jnl`	Controlling False Discovery Rates Using Null Bootstrapping. CoRR Junpei Komiyama, Masaya Abe, Kei Nakagawa, Kenichiro McAlinn
2021	J	`jnl`	Deviation-Based Learning. CoRR Junpei Komiyama, Shunya Noda
2021	J	`jnl`	Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits. CoRR Junpei Komiyama, Edouard Fouché, Junya Honda
2021	J	`jnl`	Optimal Simple Regret in Bayesian Best Arm Identification. CoRR Junpei Komiyama, Kaito Ariu, Masahiro Kato, Chao Qin
2021	J	`jnl`	Policy Choice and Best Arm Identification: Comments on "Adaptive Treatment Assignment in Experiments for Policy Choice". CoRR Kaito Ariu, Masahiro Kato, Junpei Komiyama, Kenichiro McAlinn
2020	J	`jnl`	On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach. CoRR Junpei Komiyama, Shunya Noda
2020	B	`conf`	RIC-NN: A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy. DSAA Kei Nakagawa, Masaya Abe, Junpei Komiyama
2019	J	`jnl`	A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy. CoRR Kei Nakagawa, Masaya Abe, Junpei Komiyama
2019	A*	`conf`	Scaling Multi-Armed Bandit Algorithms. KDD Edouard Fouché, Junpei Komiyama, Klemens Böhm
2018	J	`jnl`	A Simple Way to Deal with Cherry-picking. CoRR Junpei Komiyama, Takanori Maehara
2018	J	`jnl`	Comparing Fairness Criteria Based on Social Outcome. CoRR Junpei Komiyama, Hajime Shimao
2018	A*	`conf`	Nonconvex Optimization for Regression with Fairness Constraints. ICML Junpei Komiyama, Akiko Takeda, Junya Honda, Hajime Shimao
2018	J	`jnl`	UCB-SC: A Fast Variant of KL-UCB-SC for Budgeted Multi-Armed Bandit Problem. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. Ryo Watanabe, Junpei Komiyama, Atsuyoshi Nakamura, Mineichi Kudo
2017	J	`jnl`	KL-UCB-Based Policy for Budgeted Multi-Armed Bandits with Stochastic Action Costs. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. Ryo Watanabe, Junpei Komiyama, Atsuyoshi Nakamura, Mineichi Kudo
2017	—	`conf`	Position-based Multiple-play Bandit Problem with Unknown Position Bias. NIPS Junpei Komiyama, Junya Honda, Akiko Takeda
2017	—	`conf`	Road safety estimation utilizing big and heterogeneous vehicle recorder data. IEEE BigData Masashi Toyoda, Daisaku Yokoyama, Junpei Komiyama, Masahiko Itoh
2017	A*	`conf`	Statistical Emerging Pattern Mining with Multiple Testing Correction. KDD Junpei Komiyama, Masakazu Ishihata, Hiroki Arimura, Takashi Nishibayashi, Shin-ichi Minato
2017	J	`jnl`	Two-stage Algorithm for Fairness-aware Machine Learning. CoRR Junpei Komiyama, Hajime Shimao
2016	A*	`conf`	Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm. ICML Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
2016	J	`jnl`	Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm. CoRR Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
2015	A*	`conf`	Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays. ICML Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
2015	J	`jnl`	Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays. CoRR Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
2015	A*	`conf`	Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem. COLT Junpei Komiyama, Junya Honda, Hisashi Kashima, Hiroshi Nakagawa
2015	J	`jnl`	Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem. CoRR Junpei Komiyama, Junya Honda, Hisashi Kashima, Hiroshi Nakagawa
2015	—	`conf`	Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring. NIPS Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
2015	J	`jnl`	Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring. CoRR Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
2014	—	`conf`	Robust Distributed Training of Linear Classifiers Based on Divergence Minimization Principle. ECML/PKDD (2) Junpei Komiyama, Hidekazu Oiwa, Hiroshi Nakagawa
2014	—	`conf`	Time-Decaying Bandits for Non-stationary Systems. WINE Junpei Komiyama, Tao Qin
2013	C	`conf`	Multi-armed Bandit Problem with Lock-up Periods. ACML Junpei Komiyama, Issei Sato, Hiroshi Nakagawa