フォロー
Junya Honda
Junya Honda
確認したメール アドレス: i.kyoto-u.ac.jp - ホームページ
タイトル
引用先
引用先
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
1892015
Polar coding without alphabet extension for asymmetric models
J Honda, H Yamamoto
IEEE Transactions on Information Theory 59 (12), 7829-7838, 2013
1862013
An Asymptotically Optimal Bandit Algorithm for Bounded Support Models.
J Honda, A Takemura
COLT, 67-79, 2010
1632010
Nonconvex optimization for regression with fairness constraints
J Komiyama, A Takeda, J Honda, H Shimao
International conference on machine learning, 2737-2746, 2018
1292018
Learning from positive and unlabeled data with a selection bias
M Kato, T Teshima, J Honda
International conference on learning representations, 2019
1272019
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
1012015
A fully adaptive algorithm for pure exploration in linear bandits
L Xu, J Honda, M Sugiyama
International Conference on Artificial Intelligence and Statistics, 843-851, 2018
982018
Optimality of Thompson sampling for Gaussian bandits depends on priors
J Honda, A Takemura
Artificial Intelligence and Statistics, 375-383, 2014
922014
An asymptotically optimal policy for finite support models in the multiarmed bandit problem
J Honda, A Takemura
Machine Learning 85 (3), 361-391, 2011
792011
On the calibration of multiclass classification with rejection
C Ni, N Charoenphakdee, J Honda, M Sugiyama
Advances in Neural Information Processing Systems 32, 2586-2596, 2019
752019
Unsupervised domain adaptation based on source-guided discrepancy
S Kuroki, N Charoenphakdee, H Bao, J Honda, I Sato, M Sugiyama
Proceedings of the AAAI Conference on Artificial Intelligence 33, 4122-4129, 2019
642019
Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards
J Honda, A Takemura
The Journal of Machine Learning Research 16 (1), 3721-3756, 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
462016
Bandit Algorithms Based on Thompson Sampling for Bounded Reward Distributions
C Riou, J Honda
Algorithmic Learning Theory, 777-826, 2020
442020
Almost instantaneous fixed-to-variable length codes
H Yamamoto, M Tsuchihashi, J Honda
IEEE Transactions on Information Theory 61 (12), 6432-6443, 2015
432015
Good arm identification via bandit feedback
H Kano, J Honda, K Sakamaki, K Matsuura, A Nakamura, M Sugiyama
Machine Learning 108 (5), 721-745, 2019
392019
Construction of polar codes for channels with memory
R Wang, J Honda, H Yamamoto, R Liu, Y Hou
2015 IEEE Information Theory Workshop-Fall (ITW), 187-191, 2015
382015
Normal bandits of unknown means and variances
W Cowan, J Honda, MN Katehakis
The Journal of Machine Learning Research 18 (1), 5638-5665, 2017
362017
Exploring a potential energy surface by machine learning for characterizing atomic transport
K Kanamori, K Toyoura, J Honda, K Hattori, A Seko, M Karasuyama, ...
Physical Review B 97 (12), 125124, 2018
332018
Worst-case redundancy of optimal binary AIFV codes and their extended codes
W Hu, H Yamamoto, J Honda
IEEE Transactions on Information Theory 63 (8), 5074-5086, 2017
332017
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20