Taira Tsuchiya

Slides for the ELLIS Milan + RIKEN AIP Joint ELIAS Workshop [slides]

Upcoming Talks

• Feb 27, 2026: U of Tokyo Joint Seminar on Machine Learning Theory, UTokyo, Japan [slides]
• March 26–27, 2026: Workshop on the Mathematics of Online Prediction 2026 (in Japanese), Sapporo, Japan
• May 2–5, 2026: AISTATS 2026, Tangier, Morocco
• May 7–8, 2026: Joint Workshop between Università degli Studi di Milano and RIKEN, Milan, Italy
• July 5, 2026: RIKEN–Vector–NAIRL Workshop, Seoul, South Korea
• July 6–11, 2026: ICML 2026, Seoul, South Korea (presenting two papers [paper 1] [paper 2])

News

• Sep 25, 2026: One paper with a master's student, Mingyi, was accepted to NeurIPS 2026! We show that policy optimization can achieve data-dependent regret bounds (and the best-of-both-worlds guarantee) in episodic MDPs with unknown transitions (preprint).
• Jan 22, 2026: Two papers on learning in games were accepted to AISTATS 2026! The first paper (selected as a Spotlight) investigates regret upper and lower bounds for optimistic Hedge in two-player zero-sum games (preprint). The camera-ready version of the other paper is currently being prepared.
• Sep 19, 2025: Three papers were accepted to NeurIPS 2025! (1) online structured prediction under bandit and delayed feedback with last year's undergraduate thesis student, Yuki (preprint); (2) fast rates in online inverse optimization via online Newton step and MetaGrad (preprint); and (3) best-of-both-worlds algorithms in tabular MDPs with aggregate feedback.
• May 3, 2025: Happy to share that two papers were accepted to COLT 2025! One paper studies the learning dynamics in two-player zero-sum and multi-player general-sum games where players' strategies or observations may be corrupted (preprint, slides (long version), video (YouTube, 12 mins)), and the other one investigates instance-dependent regret upper and lower bounds in two-player zero-sum games (preprint).
• Jan 22, 2025: Our paper "Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis" was accepted to AISTATS 2025! The preprint is available here.
• Sep 26, 2024: Two papers were accepted to NeurIPS 2024! One paper develops a general adaptive learning rate framework for online learning with a minimax regret of $\Theta(T^{2/3})$. As an application of this framework, we consider partial monitoring, graph bandits, and bandits with paid observations, and establish improved or new best-of-both-worlds regret upper bounds. The preprint and slides are available. The second paper investigates fast rates in online convex optimization over curved feasible sets. We show that if the feasible set is enclosed by a certain sphere or is uniformly convex, algorithms adaptive to the curvature of losses can achieve fast rates. Here are the preprint and slides.
Past news (click to expand)
May 2, 2024: Papers on best-of-both-worlds algorithms were accepted: one for linear contextual bandits at AISTATS 2024 (paper) and the other for partial monitoring at ICML 2024 (paper)!
Sep 22, 2023: Our paper "Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds" was accepted to NeurIPS 2023! The preprint is available here. The paper introduces the stability-penalty-adaptive (SPA) learning rate for FTRL, establishing a regret bound jointly depending on (empirical) stability and penalty. By leveraging the new adaptive learning rate framework, we present the first best-of-both-worlds (BOBW) algorithm with a sparsity-dependent bound in bandits. Furthermore, this adaptive learning rate allows us to prove the BOBW guarantee and an empirical game-dependent bound simultaneously in partial monitoring. The camera-ready version is available here.
Jan 20, 2023: Our paper on an adaptive combinatorial semi-bandit algorithm was accepted to AISTATS 2023!

Dec 22, 2022: Two papers on best-of-both-worlds algorithms were accepted to ALT 2023—one for partial monitoring and the other for follow-the-perturbed-leader!

Publications

(α-β) indicates that the authors are listed in alphabetical order.

Preprints

1. Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity
   Mingyi Li, Taira Tsuchiya, and Kenji Yamanishi
   [arXiv]
2. Closing the Horizon Gap in Policy Optimization for Adversarial MDPs
   Mingyi Li and Taira Tsuchiya
   [arXiv]
3. Muon with Finite Newton–Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization
   (α-β) Mingyi Li and Taira Tsuchiya
   [arXiv]
4. Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization
   Taira Tsuchiya
   [arXiv]
5. Scale-Invariant Fast Convergence in Games
   Taira Tsuchiya, Haipeng Luo, and Shinji Ito
   [arXiv]
6. Reinforcement Learning from Adversarial Preferences in Tabular MDPs
   Taira Tsuchiya, Shinji Ito, and Haipeng Luo
   [arXiv]
7. Online Control of Linear Systems with Unbounded and Degenerate Noise
   Kaito Ito and Taira Tsuchiya
   [arXiv]

Conference Proceedings (peer-reviewed)

1. Policy Optimization Achieves Data-Dependent Regret Bounds in MDPs with Unknown Transitions
   Mingyi Li, Taira Tsuchiya, and Kenji Yamanishi
   [arXiv] → Accepted to NeurIPS 2026
2. A Sampling-Based Relaxation Approach to Contextual Inverse Optimization
   Yasunari Hikima, Naoyuki Kamiyama, Shinsaku Sakaue, and Taira Tsuchiya
   [paper] [arXiv] → Accepted to IJCAI-ECAI 2026
3. Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
   (α-β) Shinji Ito, Haipeng Luo, Arnab Maiti, Taira Tsuchiya, and Yue Wu
   [arXiv] → Accepted to COLT 2026
4. Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
   Mingyi Li, Taira Tsuchiya, and Kenji Yamanishi
   In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), pp.70438–70509, 2026.
   [paper] [arXiv]
5. Last-Iterate Convergence of Regularized Gradient Methods for Stochastic Monotone Variational Inequalities
   Shinji Ito, Taira Tsuchiya, Kaito Ariu, and Kenshi Abe
   In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), pp.50047–50071, 2026.
   [paper] [arXiv]
6. Optimal Learning in Games under Delayed Feedback
   Ruotong Zhuang, Taira Tsuchiya, and Shinji Ito
   In Proceedings of The 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026), pp.5266–5274, 2026.
   [paper] [arXiv (coming soon)]
7. Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
   Taira Tsuchiya
   In Proceedings of The 29th International Conference on Artificial Intelligence and Statistics (AISTATS 2026), pp.4870–4878, 2026.
   [paper] [arXiv] [slides]
   Spotlight (top 3.0% of all submitted papers)
8. Bandit and Delayed Feedback in Online Structured Prediction
   Yuki Shibukawa, Taira Tsuchiya, Shinsaku Sakaue, and Kenji Yamanishi
   In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), pp.26090–26132, 2025.
   [paper] [arXiv]
9. Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
   (α-β) Shinji Ito, Kevin Jamieson, Haipeng Luo, Arnab Maiti, and Taira Tsuchiya
   In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), pp.6915–6970, 2025.
   [paper] [arXiv]
10. Online Inverse Linear Optimization: Efficient Logarithmic-Regret Algorithm, Robustness to Suboptimality, and Lower Bound
    (Previous title: "Online Inverse Linear Optimization: Improved Regret Bound, Robustness to Suboptimality, and Toward Tight Regret Analysis")
    Shinsaku Sakaue, Taira Tsuchiya, Han Bao, and Taihei Oki
    In Advances in Neural Information Processing Systems 38 (NeurIPS 2025), pp.85189–85217, 2025.
    [paper] [arXiv]
11. Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
    (α-β) Shinji Ito, Haipeng Luo, Taira Tsuchiya, and Yue Wu
    In Proceedings of Thirty Eighth Conference on Learning Theory (COLT 2025), pp.2858–2892, 2025.
    [paper] [arXiv]
12. Corrupted Learning Dynamics in Games
    Taira Tsuchiya, Shinji Ito, and Haipeng Luo
    In Proceedings of Thirty Eighth Conference on Learning Theory (COLT 2025), pp.5506–5552, 2025.
    [paper] [arXiv] [slides (long version)] [slides (for 12 mins talk)] [video (YouTube, 12 mins)]
13. Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis
    Shinsaku Sakaue, Han Bao, and Taira Tsuchiya
    In Proceedings of The 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), pp.46–54, 2025.
    [paper] [arXiv]
14. A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
    Taira Tsuchiya and Shinji Ito
    In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pp.8477–8514, 2024.
    [paper] [arXiv] [slides] [poster]
15. Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
    Taira Tsuchiya and Shinji Ito
    In Advances in Neural Information Processing Systems 37 (NeurIPS 2024), pp.101671–101695, 2024.
    [paper] [arXiv] [slides] [poster]
16. Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
    Shinji Ito, Taira Tsuchiya, and Junya Honda
    In Proceedings of Thirty Seventh Conference on Learning Theory (COLT 2024), pp.2522–2563, 2024.
    [paper] [arXiv]
17. Online Structured Prediction with Fenchel–Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
    Shinsaku Sakaue, Han Bao, Taira Tsuchiya, and Taihei Oki
    In Proceedings of Thirty Seventh Conference on Learning Theory (COLT 2024), pp.4458–4486, 2024.
    [paper] [arXiv]
18. Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
    Taira Tsuchiya, Shinji Ito, and Junya Honda
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pp.48768–48790, 2024.
    [paper] [arXiv]
19. Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
    Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale, and Nicolò Cesa-Bianchi
    In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024), pp.1216–1224, 2024.
    [paper] [arXiv]
20. Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
    Taira Tsuchiya, Shinji Ito, and Junya Honda
    In Advances in Neural Information Processing Systems 36 (NeurIPS 2023), pp.47406–47437, 2023.
    [paper] [arXiv] [slides] [slides (short)] [poster]
21. Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits
    Taira Tsuchiya, Shinji Ito, and Junya Honda
    In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), pp.8117–8144, 2023.
    [paper] [poster]
22. Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems
    Junya Honda, Shinji Ito, and Taira Tsuchiya
    In Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), pp.726–754, 2023.
    [paper]
23. Best-of-Both-Worlds Algorithms for Partial Monitoring
    Taira Tsuchiya, Shinji Ito, and Junya Honda
    In Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), pp.1484–1515, 2023.
    [paper] [arXiv] [slides]
24. Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
    Shinji Ito, Taira Tsuchiya, and Junya Honda
    In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pp.28631–28643, 2022.
    [paper] [arXiv]
25. Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification
    Junpei Komiyama, Taira Tsuchiya, and Junya Honda
    In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pp.10393–10404, 2022.
    [paper] [arXiv]
26. Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds
    Shinji Ito, Taira Tsuchiya, and Junya Honda
    In Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), pp.1421–1422, 2022.
    [paper (extended abstract)] [full paper on arXiv] [slides]
27. Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
    Taira Tsuchiya, Junya Honda, and Masashi Sugiyama
    In Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pp.8861–8871, 2020.
    [paper] [full paper (pdf)] [arXiv] [poster]
28. Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning
    Taira Tsuchiya, Naohiro Tawara, Tetsuji Ogawa, and Tetsunori Kobayashi
    In Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), pp.2381–2385, 2018.
    [paper] [preprint]

Journal Papers (peer-reviewed)

1. Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization
   Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato, and Masashi Sugiyama
   Neural Computation, 33(12):3361–3412, 2021.
   [arXiv] [paper]

Misc (invited talks / domestic conferences / domestic proceedings / workshops)

1. Taira Tsuchiya,
   "Adaptive Online Convex Optimization and Applications to Game Theory and Reinforcement Learning,"
   Presented at OR Society of Japan Study Group: Theory and Algorithms of Optimization (RAOTA), NII, Sep 8, 2025 (in Japanese).
   Invited talk
2. Taira Tsuchiya,
   "Bridging Game Theory and Online Convex Optimization: Learning Dynamics in Games with Strategic Deviations,"
   Presented at [RIKEN AIP Research Results Event] Transforming the AI Industry through Mathematical Research, RIKEN AIP, Aug 28, 2025 (in Japanese).
   
3. Yuki Shibukawa, Taira Tsuchiya, Shinsaku Sakaue, and Kenji Yamanishi,
   "Bandit and Delayed Feedback in Online Structured Prediction,"
   Presented at 27th Information-Based Induction Sciences Workshop (IBIS 2025), Nov. 12–15, 2025.
   
4. Kei Nakagawa and Taira Tsuchiya,
   "Generalizing Risk Parity Portfolios with Weighted Tsallis Entropy Regularization,"
   Presented at The 34th JSAI Special Interest Group on Financial Informatics (SIG-FIN) (in Japanese), Mar. 1–2, 2025.
   (Best Paper Award) [link]
5. Taira Tsuchiya,
   "Advances in Best of Both Worlds Algorithms,"
   Presented at Workshop on the Mathematics of Online Prediction 2025 (in Japanese), Feb. 23–24, 2025.
   
6. Kaito Ito and Taira Tsuchiya,
   "Regret Analysis of Online Optimal Control for Linear Systems with Unbounded Noise,"
   Presented at 27th Information-Based Induction Sciences Workshop (IBIS 2024), Nov. 4–7, 2024.
   
7. Taira Tsuchiya,
   "Best of Both Worlds Algorithms in Online Decision Making Problems,"
   Presented at Machine Learning Summer School 2024, March 4–15, 2024.
   
8. Taira Tsuchiya, Shinji Ito, and Junya Honda,
   "Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds,"
   Presented at 26th Information-Based Induction Sciences Workshop (IBIS 2023), Oct. 29–Nov. 1, 2023.
   Finalist for the Outstanding Student Presentation Award [link]
9. Taira Tsuchiya,
   "Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits,"
   Presented at FIT2023, Sept. 6–8, 2023.
   Invited talk
10. Taira Tsuchiya, Shinji Ito, and Junya Honda,
    "Best-of-Both-Worlds Algorithms for Partial Monitoring,"
    Presented at JSAI SIG-FPAI, Aug. 29–30, 2023.
    JSAI Incentive Award [link]
11. Junya Honda, Shinji Ito, and Taira Tsuchiya,
    "On the Optimality of Follow-The-Perturbed-Leader Policy for Stochastic and Adversarial Settings,"
    In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop, vol.122, no.325, pp.30–37, Dec 2022.
    
12. Taira Tsuchiya,
    "Best-of-Both-Worlds Algorithms for Partial Monitoring,"
    Mathematical and Information Science Research Workshop, Dec. 15, 2022.
    
13. Taira Tsuchiya, Shinji Ito, and Junya Honda,
    "Advances in Best-of-Both-Worlds Algorithms for Bandits: Structural Bandits and Variance-Dependent Regret Bounds,"
    Presented at 25th Information-Based Induction Sciences Workshop (IBIS 2022), Nov. 20–23, 2022.
    Best Student Presentation Award [link]
14. Junpei Komiyama, Taira Tsuchiya, and Junya Honda,
    "Minimax Optimal Algorithm for Fixed-Budget Best Arm Identification,"
    Presented at 25th Information-Based Induction Sciences Workshop (IBIS 2022), Nov. 20–23, 2022.
    
15. Taira Tsuchiya,
    "Towards Practical Algorithms for Online Decision-Making,"
    Seminar talk at INRIA Lille Scool group, July 8, 2022.
    [slides]
16. Junta Fujinaga, Taira Tsuchiya, and Junya Honda,
    "On DC Relaxation of Information-directed Sampling in Combinatorial Multi-armed Bandit Problem,"
    In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop, vol.122, no.90, pp.129–136, June 2022.
    
17. Taira Tsuchiya,
    "Thompson Sampling for Partial Monitoring,"
    Toshiba Symposium 2020, Dec. 22, 2020.
    
18. Taira Tsuchiya, Junya Honda, and Masashi Sugiyama,
    "Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring,"
    Presented at 23rd Information-Based Induction Sciences Workshop (IBIS 2020), Nov. 23–26, 2020.
    Outstanding Presentation Award [link]
19. Taira Tsuchiya, Nontawat Charoenphakdee, Issei Sato, and Masashi Sugiyama,
    "Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization,"
    Presented at 22nd Information-Based Induction Sciences Workshop (IBIS 2019), Nov. 20–23, 2019.
    
20. Taira Tsuchiya, Tomoharu Iwata, and Tetsuji Ogawa,
    "Transformed Multiple Matrix Factorization: Towards Utilizing Heterogeneous Auxiliary Information,"
    In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop, vol.117, no.475, pp.41–48, March 2018.
    
21. Naohiro Tawara, Taira Tsuchiya, Tetsuji Ogawa, and Tetsunori Kobayashi,
    "Speaker Feature Extraction using Adversarial Training,"
    In Proceedings of the 2018 Spring Meeting of the Acoustical Society of Japan (ASJ 2018), pp.141–144, March 2018.
    
22. Taira Tsuchiya, Naohiro Tawara, Tetsuji Ogawa, and Tetsunori Kobayashi,
    "Adversarial Multi-Task Learning for Extracting Speaker Invariant Feature for Zero-Resource Languages,"
    In Proceedings of the 2018 Spring Meeting of the Acoustical Society of Japan (ASJ 2018), pp.9–12, March 2018.
    

Grants

1. BOOST, JST [link] (Oct. 2026 – Sep. 2031)
2. KAKENHI Grant-in-Aid for Early-Career Scientists, JSPS [link] (Apr. 2026 – Mar. 2028)
3. KAKENHI Grant-in-Aid for Research Activity Start-up, JSPS [link] (July 2024 – Mar. 2026)
4. ACT-X (Frontier of mathematics and information science, acceleration phase), JST [link] (Apr. 2024 – Mar. 2025)
5. ACT-X (Frontier of mathematics and information science), JST [link] (Oct. 2021 – Mar. 2024)
6. JSPS Research Fellowship for Young Scientists (DC1), JSPS [link]
7. AIP Challenge Program, JST (Aug. 2019 – Mar. 2020)

Awards

1. (Best Paper Award, JSAI Special Interest Group on Financial Informatics, 2025) [link (Japanese page)]
2. Ohbu Award, RIKEN, 2025 [link]
3. (IEICE TC-IBISML Research Award, IBISML, 2023)
4. JSAI Incentive Award, The Japanese Society of Artificial Intelligence, 2023 [link]
5. Finalist for the Outstanding Student Presentation Award (Top 6 of approx. 100 student presentations), IBIS2023, 2023 [link]
6. Best Student Presentation Award (1st place out of approx. 100 student presentations), IBIS2022, 2022 [link]
7. Outstanding Presentation Award (Top 5 of 118 all presentations), IBIS2020, 2020 [link]
8. Travel Award, NeurIPS 2020
9. UTokyo Toyota-Dwango AI Scholarship (Apr. 2020 – Mar. 2021)
10. UTokyo Toyota-Dwango AI Scholarship (Apr. 2019 – Mar. 2020)
11. JEES-Softbank AI Scholarship (Apr. 2019 – Mar. 2020)
12. Department Award, Waseda University, 2018

Work Experiences

1. Oct. 2026 – Present: Specially Appointed Assistant Professor, The University of Osaka (cross-appointment supported by JST BOOST)
2. Apr. 2024 – Present: Visiting Scientist, RIKEN Center for Advanced Intelligence Project
3. Oct. 2023 – Present: Assistant Professor, The University of Tokyo
4. Apr. 2021 – Sep. 2023: Research Fellowship for Young Scientists (DC1), JSPS
5. Feb. 2019 – Sep. 2023: RIKEN Center for Advanced Intelligence Project
   (Feb. 2019 – Dec. 2020, Apr. 2021 – Mar. 2022 research part-timer; Oct. 2020 – Dec. 2020 JRA; Apr. 2022 – Sep. 2023 trainee)

Education

1. Sep. 2023: Ph.D. from the Department of Systems Science, Kyoto University (supervisor: Prof. Junya Honda)
   (enrolled in the Department of Computer Science, The University of Tokyo, for the first half-year)
2. Sep. 2020: M.S. from the Department of Complexity Science, The University of Tokyo
3. Mar. 2018: B.E. from the Department of Computer Science and Engineering, Waseda University

Teaching

1. Apr. 2025 – Present: Exercise course "Probabilistic Method" at the Department of Mathematical Engineering and Information Physics, The University of Tokyo
2. Apr. 2024 – Present: Student experiment "Virtual Net Venture" at the Department of Mathematical Engineering and Information Physics, The University of Tokyo
3. Sep. 2023 – Present: Multi-instructor lecture at the Department of Mathematical Engineering and Information Physics, The University of Tokyo
   (2023, 2024: "Online Convex Optimization and Bandits", 2025: "Online Convex Optimization and Learning in Games")
4. Sep. 2023 – Present: Short exercise course "Statistical Method" at the Department of Mathematical Engineering and Information Physics, The University of Tokyo

Contact

• mail: tsuchiya [at] mist.i.u-tokyo.ac.jp