Junpei Komiyama

Publication Activity (10 Years)

Years Active: 2013-2024
Publications (10 Years): 35

Top Topics

Contextual Bandit

Monte Carlo Tree Search

Top Venues

Publications

Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki
Fixed Confidence Best Arm Identification in the Bayesian Setting. CoRR (2024)
Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki
Learning Fair Division from Bandit Feedback. AISTATS (2024)
Junpei Komiyama, Shinji Ito, Yuichi Yoshida, Souta Koshino
Replicability is Asymptotically Free in Multi-armed Bandits. CoRR (2024)
Nishant A. Mehta, Junpei Komiyama, Vamsi K. Potluru, Andrea Nguyen, Mica Grant-Hagen
Thresholded linear bandits. AISTATS (2023)
Junpei Komiyama, Masaaki Imaizumi
High-dimensional Contextual Bandit Problem without Sparsity. NeurIPS (2023)
Hakuei Yamada, Junpei Komiyama, Kenshi Abe, Atsushi Iwasaki
Learning Fair Division from Bandit Feedback. CoRR (2023)
Junpei Komiyama, Masaaki Imaizumi
High-dimensional Contextual Bandit Problem without Sparsity. CoRR (2023)
Koji Tabata, Junpei Komiyama, Atsuyoshi Nakamura, Tamiki Komatsuzaki
Posterior Tracking Algorithm for Classification Bandits. AISTATS (2023)
Junpei Komiyama
Bayes Optimal Algorithm is Suboptimal in Frequentist Best Arm Identification. CoRR (2022)
Junpei Komiyama, Taira Tsuchiya, Junya Honda
Globally Optimal Algorithms for Fixed-Budget Best Arm Identification. CoRR (2022)
Kenshi Abe, Junpei Komiyama, Atsushi Iwasaki
Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search. CoRR (2022)
Kenshi Abe, Junpei Komiyama, Atsushi Iwasaki
Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search. IJCAI (2022)
Junpei Komiyama, Gustavo Malkomes, Bolong Cheng, Michael McCourt
Bridging Offline and Online Experimentation: Constraint Active Search for Deployed Performance Optimization. Trans. Mach. Learn. Res. 2022 (2022)
Junpei Komiyama, Taira Tsuchiya, Junya Honda
Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification. NeurIPS (2022)
Katherine Hoffmann Pham, Junpei Komiyama
Strategic Choices of Migrants and Smugglers in the Central Mediterranean Sea. CoRR (2022)
Junpei Komiyama, Shunya Noda
Deviation-Based Learning. CoRR (2021)
Junpei Komiyama, Edouard Fouché, Junya Honda
Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits. CoRR (2021)
Kaito Ariu, Masahiro Kato, Junpei Komiyama, Kenichiro McAlinn
Policy Choice and Best Arm Identification: Comments on "Adaptive Treatment Assignment in Experiments for Policy Choice". CoRR (2021)
Junpei Komiyama, Kaito Ariu, Masahiro Kato, Chao Qin
Optimal Simple Regret in Bayesian Best Arm Identification. CoRR (2021)
Junpei Komiyama, Masaya Abe, Kei Nakagawa, Kenichiro McAlinn
Controlling False Discovery Rates Using Null Bootstrapping. CoRR (2021)
Kei Nakagawa, Masaya Abe, Junpei Komiyama
RIC-NN: A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy. DSAA (2020)
Junpei Komiyama, Shunya Noda
On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach. CoRR (2020)
Edouard Fouché, Junpei Komiyama, Klemens Böhm
Scaling Multi-Armed Bandit Algorithms. KDD (2019)
Kei Nakagawa, Masaya Abe, Junpei Komiyama
A Robust Transferable Deep Learning Framework for Cross-sectional Investment Strategy. CoRR (2019)
Junpei Komiyama, Akiko Takeda, Junya Honda, Hajime Shimao
Nonconvex Optimization for Regression with Fairness Constraints. ICML (2018)
Junpei Komiyama, Hajime Shimao
Comparing Fairness Criteria Based on Social Outcome. CoRR (2018)
Ryo Watanabe, Junpei Komiyama, Atsuyoshi Nakamura, Mineichi Kudo
UCB-SC: A Fast Variant of KL-UCB-SC for Budgeted Multi-Armed Bandit Problem. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (3) (2018)
Junpei Komiyama, Takanori Maehara
A Simple Way to Deal with Cherry-picking. CoRR (2018)
Junpei Komiyama, Hajime Shimao
Two-stage Algorithm for Fairness-aware Machine Learning. CoRR (2017)
Ryo Watanabe, Junpei Komiyama, Atsuyoshi Nakamura, Mineichi Kudo
KL-UCB-Based Policy for Budgeted Multi-Armed Bandits with Stochastic Action Costs. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. (11) (2017)
Masashi Toyoda, Daisaku Yokoyama, Junpei Komiyama, Masahiko Itoh
Road safety estimation utilizing big and heterogeneous vehicle recorder data. IEEE BigData (2017)
Junpei Komiyama, Junya Honda, Akiko Takeda
Position-based Multiple-play Bandit Problem with Unknown Position Bias. NIPS (2017)
Junpei Komiyama, Masakazu Ishihata, Hiroki Arimura, Takashi Nishibayashi, Shin-ichi Minato
Statistical Emerging Pattern Mining with Multiple Testing Correction. KDD (2017)
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm. ICML (2016)
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm. CoRR (2016)
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring. NIPS (2015)
Junpei Komiyama, Junya Honda, Hisashi Kashima, Hiroshi Nakagawa
Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem. CoRR (2015)
Junpei Komiyama, Junya Honda, Hisashi Kashima, Hiroshi Nakagawa
Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem. COLT (2015)
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Regret Lower Bound and Optimal Algorithm in Finite Stochastic Partial Monitoring. CoRR (2015)
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays. ICML (2015)
Junpei Komiyama, Junya Honda, Hiroshi Nakagawa
Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays. CoRR (2015)
Junpei Komiyama, Tao Qin
Time-Decaying Bandits for Non-stationary Systems. WINE (2014)
Junpei Komiyama, Hidekazu Oiwa, Hiroshi Nakagawa
Robust Distributed Training of Linear Classifiers Based on Divergence Minimization Principle. ECML/PKDD (2) (2014)
Junpei Komiyama, Issei Sato, Hiroshi Nakagawa
Multi-armed Bandit Problem with Lock-up Periods. ACML (2013)