RIKEN AIP Center, AI Safety and Reliability Unit

Researcher.

E-mail : daisuke.hatano[ a t ]riken.jp

Google scholar, DBLP

Reserch Interest

• Multi-agent system:  Distributed optimization, Game theory,  Cooperative game, 

• Machine learning: Bandit, Fairness on machine learning 

• Optimization: Discrete optimization,  Optimization with SAT,  CSP

Journal Papers

1. 波多野 大督, 平山勝敏: 値推移コスト付き動的制約充足問題とその解法, 人工知能学会論文誌, Vol.28, No.1, pp.34-42, 2013.

2. 波多野 大督, 平山勝敏: 値変更コスト付き動的SATの定式化とその解法, 人工知能学会論文誌, Vol.26, No.6, pp.682-691, 2011.

Refereed Conference Papers

1. Koji Ichikawa, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-Ichi Kawarabayashi, New classes of the greedy-applicable arm feature distributions in the sparse linear bandit problem, AAAI2024,[link][arXiv].

2. Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-Ichi Kawarabayashi,   Bandit Task Assignment with Unknown Processing Time, NeurIPS2023, [link].

3. Hanna Sumita, Shinji Ito, Kei Takemura, Daisuke Hatano, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Online Task Assignment Problems with Reusable Resources, AAAI2022, [link] [arXiv].

4. Kei Takemura, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi:  A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits, AISTATS2021, [link].

5. Kei Takemura, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Near-Optimal Regret Bounds for Contextual Combinatorial Semi-Bandits with Linear Payoff Functions, AAAI2021, [link]. 

6. Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Delay and Cooperation in Nonstochastic Linear Bandits, NeurIPS 2020, [link].

7. Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback, NeurIPS 2019, [link].

8. Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Improved Regret Bounds for Bandit Combinatorial Optimization, NeurIPS 2019, [link].

9. Daisuke Hatano, Yuko Kuroki, Yasushi Kawase, Hanna Sumita, Naonori Kakimura, Ken-ichi Kawarabayashi: Non-zero-sum Stackelberg Budget Allocation Game for Computational Advertising, PRICAI 2019 [link] [arXiv].

10. Shinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Regret Bounds for Online Portfolio Selection with a Cardinality Constraint, NeurIPS 2018 [link].

11. Akihiro Yabe, Daisuke Hatano, Hanna Sumita, Shinji Ito, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Causal Bandits with Propagating Inference, ICML 2018 [link] [arXiv]

12. Daisuke Hatano, Yuichi Yoshida: Computational Aspects of the Preference Cores of Supermodular Two-Scenario Cooperative Games, IJCAI 2018. [link]

13. Shinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Online Regression with Partial Information: Generalization and Linear Projection, AISTATS 2018. [link]

14. Shinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi: Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation, NIPS 2017. [link]

15. Daisuke Hatano, Takuro Fukunaga, Takanori Maehara, Ken-ichi Kawarabayashi: Scalable Algortihm for Higher-order Co-clustering via Random Sampling, AAAI 2017. [link]

16. Daisuke Hatano, Yuichi Yoshida: Computing Least Cores of Supermodular Cooperative Games, AAAI 2017. [link]

17. Daisuke Hatano, Takuro Fukunaga, Ken-ichi Kawarabayashi: Adaptive Budget Allocation for Maximizing Influence of Advertisements, IJCAI 2016. [link]

18. Daisuke Hatano, Yuichi Yoshida: Distributed Multiplicative Weights Methods for DCOP, AAAI 2015. [link]

19. Daisuke Hatano, Takuro Fukunaga, Takanori Maehara, Ken-ichi Kawarabayashi: Lagrangian Decomposition Algorithm for Allocating Marketing Channels, AAAI 2015. [link]

20. Daisuke Hatano, Katsutoshi Hirayama: DeQED: An Efficient Divide-and-Coordinate Algorithm for DCOP, IJCAI 2013. [link]

21. Daisuke Hatano, Katsutoshi Hirayama: DeQED: An Efficient Divide-and-Coordinate Algorithm for DCOP, AAMAS 2013. (Extended Abstract) [link]

22. Daisuke Hatano, Katsutoshi Hirayama: Dynamic SAT with Decision Change Costs: Formalization and Solutions, IJCAI 2011. [link]

Workshop/Symposium Papers

1.  新 恭兵, 荒井 ひろみ, 小山 聡, 波多野 大督: ラベルの多様性を考慮したDawid-Skeneモデルの拡張, JSAI2024.

2. 波多野 大督, 原 聡,  荒井 ひろみ: 限界貢献を利用した不公平なモデルの修正, JSAI2023.

3. 波多野 大督:ポセットアンチマトロイド上の協力ゲームにおける効率的なシャプレイ値計算, JSAI2021. 

4. 波多野 大督, 花田研太: 分散MaxSATに対する相関均衡点の求め方に関する一検討, JSAI 2016.

5. Tenda Okimoto, Katsutoshi Hirayama, Katsumi Inoue, Daisuke Hatano, Kenta Hanada, Maxime Clement, Tony Ribeiro, Shih-Min Wu: Dynamic Scheduling for Disaster Medical Assistance Team, JAWS 2015.

6. 波多野 大督, 吉田悠一: 乗算型重み更新法に基づく分散制約快適化アルゴリズム, JSAI 2014.

7. 波多野 大督, 平山 勝敏: DeQED: 複雑な局所問題を伴う分散制約最適化問題のためのアルゴリズム, JAWS 2012.

8. 波多野 大督, 平山 勝敏: DeQED: 双対変数の値を交換する分散制約最適化アルゴリズム, JSAI 2012.

9. 波多野 大督, 平山 勝敏：値変更コスト付き動的CSPの定式化とその解法, JSAI 2011.

10. Katsutoshi Hirayama, Daisuke Hatano, Yuta Sugimoto: Model Tracking for Dynamic SAT with Decision Change Costs, SofT 2010.

11. 波多野 大督，杉本 雄太，平山 勝敏：値変更コスト付き動的SATのためのモデル追跡，JAWS 2010.

Awards

1. 論文編集貢献賞，情報処理学会，2020.

2. Best reviewer, NeurIPS, 2019.

3. 学生優秀論文賞，Joint Agent Workshop and Symposium (JAWS)，2012.

4. 海事科学部学生奨励賞，神戸大学海事科学部，2008.

Education

• 2010-2013, Graduate school of maritime science, Kobe university. 

• 2008-2010, Graduate school of maritime science, Kobe university. 

• 2004-2008, Faculty of maritime science, Kobe university. 

Employment

• 2023-present, Researcher, Advanced Intelligence Project Center, RIKEN.

• 2018-2023, Postdoc researcher, Advanced Intelligence Project Center, RIKEN.

• 2013-2018, Project researcher, Kawarabayashi ERATO Large Graph Project, National Institute of Infomatics.