| Learning from positive and unlabeled data with a selection bias M Kato, T Teshima, J Honda International Conference on Learning Representations (ICLR), 2018 | 44 | 2018 |
| Off-policy evaluation and learning for external validity under a covariate shift M Kato, M Uehara, S Yasui Advances in Neural Information Processing Systems (NeurIPS), 2020 | 24* | 2020 |
| Non-negative bregman divergence minimization for deep direct density ratio estimation M Kato, T Teshima International Conference on Machine Learning (ICML), 2021 | 10 | 2021 |
| Alternate estimation of a classifier and the class-prior from positive and unlabeled data M Kato, L Xu, G Niu, M Sugiyama arXiv preprint arXiv:1809.05710, 2018 | 10 | 2018 |
| Adaptive experimental design for efficient treatment effect estimation M Kato, T Ishihara, J Honda, Y Narita arXiv preprint arXiv:2002.05308, 2020 | 7* | 2020 |
| Optimal Simple Regret in Bayesian Best Arm Identification J Komiyama, K Ariu, M Kato, C Qin arXiv preprint arXiv:2111.09885, 2021 | 4 | 2021 |
| Off-policy evaluation of bandit algorithm from dependent samples under batch update policy M Kato, Y Kaneko arXiv preprint arXiv:2010.13554, 2020 | 4 | 2020 |
| The Role of Contextual Information in Best Arm Identification M Kato, K Ariu arXiv preprint arXiv:2106.14077, 2021 | 3 | 2021 |
| The Adaptive Doubly Robust Estimator and a Paradox Concerning Logging Policy M Kato, K McAlinn, S Yasui Neural Information Processing Systems (NeurIPS), 2021 | 3* | 2021 |
| Density-Ratio Based Personalised Ranking from Implicit Feedback R Togashi, M Kato, M Otani, S Satoh The Web Conference (WWW), 2021 | 2 | 2021 |
| A practical guide of off-policy evaluation for bandit problems M Kato, K Abe, K Ariu, S Yasui arXiv preprint arXiv:2010.12470, 2020 | 2 | 2020 |
| Mean-Variance Efficient Reinforcement Learning by Expected Quadratic Utility Maximization M Kato, K Nakagawa, K Abe, T Morimura | 2* | 2020 |
| Best Arm Identification with a Fixed Budget under a Small Gap M Kato, K Ariu, M Imaizumi, M Uehara, M Nomura, C Qin stat 1050, 11, 2022 | 1 | 2022 |
| Atro: Adversarial training with a rejection option M Kato, Z Cui, Y Fukuhara arXiv preprint arXiv:2010.12905, 2020 | 1 | 2020 |
| Learning Classifiers under Delayed Feedback with a Time Window Assumption M Kato, S Yasui arXiv preprint arXiv:2009.13092, 2020 | 1 | 2020 |
| Confidence interval for off-policy evaluation from dependent samples via bandit algorithm: Approach from standardized martingales M Kato arXiv preprint arXiv:2006.06982, 2020 | 1 | 2020 |
| Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metrics M Kato, M Imaizumi, K Minami arXiv preprint arXiv:2201.13127, 2022 | | 2022 |
| Learning Causal Models from Conditional Moment Restrictions by Importance Weighting M Kato, M Imaizumi, K McAlinn, S Yasui, H Kakehi International Conference on Learning Representations (ICLR), 2021 | | 2021 |
| Policy Choice and Best Arm Identification: Comments on" Adaptive Treatment Assignment in Experiments for Policy Choice" K Ariu, M Kato, J Komiyama, K McAlinn arXiv preprint arXiv:2109.08229, 2021 | | 2021 |
| Scalable Personalised Item Ranking through Parametric Density Estimation R Togashi, M Kato, M Otani, T Sakai, S Satoh Conference on Research and Development in Information Retrieval (SIGIR), 2021 | | 2021 |
Junya HondaKyoto University / RIKENVerified email at i.kyoto-u.ac.jp
