Publications

Tatsuhiro Shimizu, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Kei Tateno, Takuma Udagawa, Yuta Saito (2025). Off-Policy Evaluation and Learning for the Future under Non-Stationarity. In Proceedings of the 31th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD).

引用 OpenReview

Yuta Saito, Jihan Yao, Thorsten Joachims (2025). POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR) (Spotlight).

引用 OpenReview

Yuta Natsubori, Masataka Ushiku, Yuta Saito (2025). Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR) (Acceptance Rate=31%).

引用 OpenReview

Rikiya Takehi, Masahiro Asami, Kosuke Kawakami, Yuta Saito (2025). A General Framework for Off-Policy Learning with Partially-Observed Reward. In Proceedings of the Thirteenth International Conference on Learning Representations (ICLR) (Acceptance Rate=31%).

引用 OpenReview

Tatsuhiro Shimizu, Koichi Tanaka, Ren Kishimoto, Haruka Kiyohara, Masahiro Nomura, Yuta Saito (2024). Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits. In Proceedings of the 18th ACM Conference on Recommender Systems (RecSys).

引用

齋藤優太 (2024). 反実仮想機械学習. 技術評論社.

アマゾン 出版社ページ 紹介スライド

Yuta Saito, Masahiro Nomura (2024). Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It. In Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI) (Acceptance rate=15%).

引用 Proceedings

Riku Togashi, Kenshi Abe, Yuta Saito (2024). Scalable and Provably Fair Exposure Control for Large-Scale Recommender Systems. In Proceedings of the ACM Web Conference 2024 (TheWebConf) (Acceptance Rate=20.2%).

引用 動画 arXiv Proceedings

Haruka Kiyohara, Masahiro Nomura, Yuta Saito (2024). Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction. In Proceedings of the ACM Web Conference 2024 (TheWebConf) (Acceptance Rate=20.2%).

引用 コード arXiv Proceedings

Yuta Saito, Himan Abdollahpouri, Jesse Anderton, Ben Carterette, Mounia Lalmas (2024). Long-term Off-Policy Evaluation and Learning. In Proceedings of the ACM Web Conference 2024 (TheWebConf) (Acceptance Rate=20.2%).

引用 コード arXiv Proceedings

Haruka Kiyohara, Ren Kishimoto, Kosuke Kawakami, Ken Kobayashi, Kazuhide Nakata, Yuta Saito (2024). Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR) (Acceptance Rate=31%).

引用 コード arXiv

Haruka Kiyohara, Tatsuya Matsuhiro, Yusuke Narita, Nobuyuki Shimizu, Yasuo Yamamoto, Yuta Saito (2023). Off-Policy Evaluation of Ranking Policies under Diverse User Behavior. In Proceedings of the 29th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (Acceptance rate=22.3%).

引用 コード ポスター スライド arXiv Proceedings

Yuta Saito, Qingyang Ren, Thorsten Joachims (2023). Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling. In Proceedings of the 40th International Conference on Machine Learning (ICML) (Acceptance rate=27.9%).

引用 コード ポスター スライド arXiv Proceedings

神嶌 敏弘, 齋藤優太 (2023). 会議報告：The 16th ACM Conference on Recommender Systems（RecSys 2022）. 人工知能, Vol.38, No.1.

学会誌

Takuma Udagawa, Haruka Kiyohara, Yusuke Narita, Yuta Saito, Kei Tateno (2022). Policy-Adaptive Estimator Selection for Off-Policy Evaluation. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI) (Acceptance rate=19.6%).

引用 コード スライド arXiv

齋藤優太 (2022). オフ方策評価の基礎と動向. 人工知能, Vol.37, No.4.

学会誌

Yuta Saito, Thorsten Joachims (2022). Counterfactual Evaluation and Learning for Interactive Systems. In Proceedings of the 28th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD).

引用 コード 会議録 Website

Yuta Saito, Thorsten Joachims (2022). Fair Ranking as Fair Division: Impact-Based Individual Fairness in Ranking. In Proceedings of the 28th SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) (Acceptance rate=14.9%).

引用 コード 動画 スライド arXiv 会議録

Yuta Saito, Thorsten Joachims (2022). Off-Policy Evaluation for Large Action Spaces via Embeddings. In Proceedings of 39th International Conference on Machine Learning (ICML) (Acceptance rate=21.9%).

引用 コード 動画 スライド arXiv Proceedings

Yuta Saito, Masahiro Nomura (2022). Towards Resolving Propensity Contradiction in Offline Recommender Learning. In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI) (Acceptance rate=15%, Long Talk (top 25% of accepted papers)).

引用 Proceedings

Yuta Saito, Suguru Yaginuma, Taketo Naito, Kazuhide Nakata (2022). Unbiased Recommender Learning from Biased Graded Implicit Feedback. WSDM 2022 Workshop on Decision Making for Modern Information Retrieval System.

引用 PDF

Haruka Kiyohara, Yuta Saito, Tatsuya Matsuhiro, Yusuke Narita, Nobuyuki Shimizu, Yasuo Yamamoto (2022). Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model. In Proceedings of the 15th International Conference on Web Search and Data Mining (WSDM) (Acceptance rate=20.2%, Best Paper Runner-Up).

引用 コード arXiv 会議録

神嶌 敏弘, 齋藤優太 (2022). 会議報告：The 15th ACM Conference on Recommender Systems（RecSys 2021）. 人工知能, Vol.37, No.1.

学会誌

Yuta Saito, Shunsuke Aihara, Megumi Matsutani, Yusuke Narita (2021). Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation. In Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks.

引用 コード データセット 会議録 arXiv

Daisuke Moriwaki, Yuta Hayakawa, Isshu Munemasa, Yuta Saito, Akira Matsui, Masashi Shibata (2021). A Real-World Implementation of Unbiased Lift-based Bidding System. In Proceedings of the 2021 IEEE International Conference on Big Data (IEEE BigData).

引用

Masahiro Nomura, Yuta Saito (2021). Efficient Hyperparameter Optimization under Multi-Source Covariate Shift. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management (CIKM).

引用 コード 会議録 arXiv

Yuta Saito, Takuma Udagawa, Haruka Kiyohara, Kazuki Mogi, Yusuke Narita, Kei Tateno (2021). Evaluating the Robustness of Off-Policy Evaluation. In Proceedings of the 15th ACM Conference on Recommender Systems (RecSys).

引用 コード スライド 会議録 arXiv

Yuta Saito, Thorsten Joachims (2021). Counterfactual Learning and Evaluation for Recommender Systems. In Proceedings of the 15th ACM Conference on Recommender Systems (RecSys).

引用 コード プロジェクト 会議録

Haruka Kiyohara, Kosuke Kawakami, Yuta Saito (2021). Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation. RecSys 2021 Workshop on Simulation Methods for Recommender Systems.

引用 arXiv

齋藤優太, 安井翔太 (2021). 施策デザインのための機械学習入門. 技術評論社.

アマゾン 出版社ページ

Nathan Kallus, Yuta Saito, Masatoshi Uehara (2021). Optimal Off-Policy Evaluation from Multiple Logging Policies. In Proceedings of 38th International Conference on Machine Learning (ICML).

引用 コード 会議録 arXiv

成田 悠輔, 粟飯原 俊介, 齋藤優太, 松谷 恵, 矢田 紘平 (2020). 自然実験としてのアルゴリズム：機械学習・市場設計・公共政策への統一アプローチ. RIETI Discussion Paper Series 20-J-045.

ディスカッション・ペーパー

Yuta Saito (2020). Doubly Robust Estimator for Ranking Metrics with Post-Click Conversions. In Proceedings of the 14th ACM Conference on Recommender Systems (RecSys).

引用 コード スライド 会議録

Yuta Saito, Takuma Udagawa, Kei Tateno (2020). Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service. RecSys 2020 Workshop on Bandit and Reinforcement Learning from User Interactions.

引用 arXiv

Yuta Saito (2020). Unbiased Pairwise Learning from Biased Implicit Feedback. In Proceedings of the 2020 ACM SIGIR on International Conference on Theory of Information Retrieval (ICTIR).

引用 コード 会議録

Daisuke Moriwaki, Yuta Hayakawa, Isshu Munemasa, Yuta Saito, Akira Matsui (2020). Unbiased lift-based bidding system. AdKDD & TargetAd 2020 Workshop (held in conjunction with KDD2020).

引用 arXiv

Yuta Saito, Gota Morishita, Shota Yasui (2020). Dual Learning Algorithm for Delayed Conversions. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).

引用 スライド 会議録

Yuta Saito, Shota Yasui (2020). Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models. In Proceedings of 37th International Conference on Machine Learning (ICML).

引用 コード スライド 会議録

Yuta Saito (2020). Asymmetric Tri-training for Debiasing Missing-Not-At-Random Explicit Feedback. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR).

引用 コード スライド 会議録

齋藤優太 (2020). 私のブックマーク：反実仮想機械学習 (Counterfactual Machine Learning, CFML). 人工知能, Vol.35, No.4.

学会誌 ウェブ版

成田 悠輔, 粟飯原 俊介, 齋藤優太, 松谷 恵, 矢田 紘平 (2020). すべての機械学習は A/B テストである. 人工知能, Vol.35, No.4.

学会誌

Yuta Saito, Hayato Sakata, Kazuhide Nakata (2020). Cost-Effective and Stable Policy Optimization Algorithm for Uplift Modeling with Multiple Treatments. In Proceedings of the 2020 SIAM International Conference on Data Mining (SDM).

引用 会議録

Yuta Saito, Suguru Yaginuma, Yuta Nishino, Hayato Sakata, Kazuhide Nakata (2020). Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback. In Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM).

引用 コード スライド 会議録

Yuta Saito, Hayato Sakata, Kazuhide Nakata (2019). Doubly Robust Prediction and Evaluation Methods Improve Uplift Modeling for Observational Data. In Proceedings of the 2019 SIAM International Conference on Data Mining (SDM).

引用 会議録