Follow
Junpei Komiyama
Junpei Komiyama
New York University
Verified email at komiyama.info - Homepage
Title
Cited by
Cited by
Year
Optimal regret analysis of thompson sampling in stochastic multi-armed bandit problem with multiple plays
J Komiyama, J Honda, H Nakagawa
International Conference on Machine Learning, 1152-1161, 2015
1442015
Nonconvex optimization for regression with fairness constraints
J Komiyama, A Takeda, J Honda, H Shimao
International conference on machine learning, 2737-2746, 2018
762018
Regret lower bound and optimal algorithm in dueling bandit problem
J Komiyama, J Honda, H Kashima, H Nakagawa
Conference on learning theory, 1141-1154, 2015
602015
Copeland dueling bandit problem: Regret lower bound, optimal algorithm, and computationally efficient algorithm
J Komiyama, J Honda, H Nakagawa
International Conference on Machine Learning, 1235-1244, 2016
252016
Scaling multi-armed bandit algorithms
E Fouché, J Komiyama, K Böhm
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019
202019
Position-based multiple-play bandit problem with unknown position bias
J Komiyama, J Honda, A Takeda
Advances in Neural Information Processing Systems 30, 2017
202017
Statistical emerging pattern mining with multiple testing correction
J Komiyama, M Ishihata, H Arimura, T Nishibayashi, S Minato
Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge …, 2017
192017
Regret lower bound and optimal algorithm in finite stochastic partial monitoring
J Komiyama, J Honda, H Nakagawa
Advances in Neural Information Processing Systems 28, 2015
192015
Multi-armed bandit problem with lock-up periods
J Komiyama, I Sato, H Nakagawa
Asian Conference on Machine Learning, 100-115, 2013
162013
Two-stage algorithm for fairness-aware machine learning
J Komiyama, H Shimao
arXiv preprint arXiv:1710.04924, 2017
142017
Time-decaying bandits for non-stationary systems
J Komiyama, T Qin
International Conference on Web and Internet Economics, 460-466, 2014
132014
RIC-NN: a robust transferable deep learning framework for cross-sectional investment strategy
K Nakagawa, M Abe, J Komiyama
2020 IEEE 7th International Conference on Data Science and Advanced …, 2020
82020
KL-UCB-based policy for budgeted multi-armed bandits with stochastic action costs
R Watanabe, J Komiyama, A Nakamura, M Kudo
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and …, 2017
62017
Optimal simple regret in bayesian best arm identification
J Komiyama, K Ariu, M Kato, C Qin
arXiv preprint arXiv:2111.09885, 2021
42021
Comparing fairness criteria based on social outcome
J Komiyama, H Shimao
arXiv preprint arXiv:1806.05112, 2018
42018
Policy choice and best arm identification: Asymptotic analysis of exploration sampling
K Ariu, M Kato, J Komiyama, K McAlinn, C Qin
arXiv preprint arXiv:2109.08229, 2021
32021
On Statistical Discrimination as a Failure of Social Learning: A Multi-Armed Bandit Approach
J Komiyama, S Noda
arXiv preprint arXiv:2010.01079, 2020
32020
Cross validation based model selection via generalized method of moments
J Komiyama, H Shimao
arXiv preprint arXiv:1807.06993, 2018
32018
Anytime Capacity Expansion in Medical Residency Match by Monte Carlo Tree Search
K Abe, J Komiyama, A Iwasaki
arXiv preprint arXiv:2202.06570, 2022
12022
Finite-time analysis of globally nonstationary multi-armed bandits
J Komiyama, E Fouché, J Honda
arXiv preprint arXiv:2107.11419, 2021
12021
The system can't perform the operation now. Try again later.
Articles 1–20