Taira Tsuchiya

Japanese version is here．

News

• Jan 20, 2023: Our paper on an adaptive combinatorial semi-bandit algorithm was accepted at AISTATS 2023!
  
• Dec 22, 2022: Two papers on the best-of-both-worlds algorithm were accepted at ALT 2023 - one for partial monitoring and the other for follow-the-perturbated-leader!
  
• Sep 14, 2022: Our papers on (near-)optimal best-of-both-worlds algorithms for online learning with feedback graphs [link] and (minimax) optimal best arm identification for the fixed-budget setting [link] are accepted by NeurIPS2022!
  
• Jul 29, 2022: Our new paper on best-of-both-worlds algorithms for partial monitoring is on arXiv [link].
  
• Jul 5, 2022: Happy to stay at INRIA Lille Scool group for one week and give a talk with the title "Towards Practical Algorithms for Online Decision-Making"! The slide is available here．
  
• Jul 4, 2022: Presented a best-of-both-worlds algorithm with a variance-dependent regret bound at COLT2022! The slide is available here．
  
• Sep 21, 2021: My research proposal has been accepted by JST ACT-X (Frontier of mathematics and information science). [link (in Japanese)]
• May 28, 2021: Our paper "Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization" has been accepted by Neural Computation!
  
• Apr 1, 2021: Moved to Kyoto University due to the transfer of my supervisor.
• Jan 8, 2021: We recieved the outstanding presentation award at IBIS2020! [link]
• Sep 26, 2020: Our paper "Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring" has been accepted by NeurIPS2020!
  We present a novel Thompson-sampling-based algorithm, which empirically works very well in partial monitoring games, and prove that the new algorithm achieves the logarithmic problem-dependent expected regret for problems with local observability. This result is the first regret bound of Thompson sampling for partial monitoring, which also becomes the first logarithmic regret bound of Thompson sampling for linear bandits. The preprint can be obtained from here. The camera-ready version will be available within a month. The pre-proceeding is now available here. The final camera-ready version is now available here.

Publications

Preprints

1. Taira Tsuchiya, Shinji Ito, and Junya Honda,
   "Stability-penalty-adaptive Follow-the-regularized-leader: Sparsity, Game-dependency, and Best-of-both-worlds,"
   arXiv:2305.17301, 2023.
   [arXiv]
   

Conference Proceedings (peer-reviewed)

1. Taira Tsuchiya, Shinji Ito, and Junya Honda,
   "Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits,"
   In Proceedings of 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), pp.8117–8144, 2023.
   (Presented at International Conference on Artificial Intelligence and Statistics (AISTATS 2023), Valencia, Spain, Apr. 25–Apr. 28, 2023)
   [proceeding] [poster]
   
2. Junya Honda, Shinji Ito, and Taira Tsuchiya,
   "Follow-the-Perturbed-Leader Achieves Best-of-Both-Worlds for Bandit Problems,"
   In Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), pp.726–754, 2023.
   (Presented at International Conference on Algorithmic Learning Theory (ALT 2023), Singapore, Feb. 20–23, 2023)
   [proceeding]
   
3. Taira Tsuchiya, Shinji Ito, and Junya Honda,
   "Best-of-Both-Worlds Algorithms for Partial Monitoring,"
   In Proceedings of The 34th International Conference on Algorithmic Learning Theory (ALT 2023), pp.1484–1515, 2023.
   (Presented at International Conference on Algorithmic Learning Theory (ALT 2023), Singapore, Feb. 20–23, 2023)
   [arXiv] [proceeding] [slide]
   
4. Shinji Ito, Taira Tsuchiya, and Junya Honda,
   "Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs,"
   In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pp.28631–28643, 2022.
   (Presented at Neural Information Processing Systems (NeurIPS 2022), New Orleans, Louisiana, USA, Nov. 28–Dec. 9, 2022)
   [proceeding] [arXiv]
   
5. Junpei Komiyama, Taira Tsuchiya, and Junya Honda,
   "Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification,"
   In Advances in Neural Information Processing Systems 35 (NeurIPS 2022), pp.10393–10404, 2022.
   (Presented at Neural Information Processing Systems (NeurIPS 2022), New Orleans, Louisiana, USA, Nov. 28–Dec. 9, 2022)
   [proceeding] [arXiv]
   
6. Shinji Ito, Taira Tsuchiya, and Junya Honda,
   "Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds,"
   In Proceedings of Thirty Fifth Conference on Learning Theory (COLT 2022), pp.1421–1422, 2022.
   (Presented at Conference on Learning Theory (COLT 2022), London, UK, July 2–5, 2022)
   [proceeding (extended abstract)] [full paper on arXiv] [slide]
   
7. Taira Tsuchiya, Junya Honda, and Masashi Sugiyama,
   "Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring,"
   In Advances in Neural Information Processing Systems 33 (NeurIPS 2020), pp.8861–8871, 2020.
   (Presented at Neural Information Processing Systems (NeurIPS2020), online, Dec. 6–12, 2020)
   [proceeding] [full paper (pdf)] [arXiv] [poster]
   
8. Taira Tsuchiya, Naohiro Tawara, Tetsuji Ogawa, and Tetsunori Kobayashi,
   "Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning,"
   In Proceedings of 2018 IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2018), pp.2381–2385, 2018.
   (Presented at International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2018), Calgary, Canada, Apr. 15–20, 2018)
   [preprint] [paper]
   

Journal Papers (peer-reviewed)

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

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

1. Junya Honda, Shinji Ito, and Taira Tsuchiya,
   "On the Optimality of Follow-The-Perturbated-Leader Policy for Stochastic and Adversarial Settings"
   In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop, vol.xxx, no.xx, pp.xxx–xxx, Dec 2022.
   
2. Taira Tsuchiya,
   "Best-of-Both-Worlds Algorithms for Partial Monitoring,"
   (Ja), Dec. 15, 2022.
   
3. 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.
   Recieved best studenet presentation award. [link]
4. 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.
   
5. Taira Tsuchiya,
   "Towards Practical Algorithms for Online Decision-Making,"
   Seminar talk at INRIA Lille Scool group, July 8, 2022.
   [slide]
6. 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.
   
7. Taira Tsuchiya,
   "Thompson Sampling for Partial Monitoring,"
   Toshiba Sympsium 2020, Dec. 22, 2020.
   
8. 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.
   Recieved outstanding presentation award. [link]
9. 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.
   
10. 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.
    
11. Naohiro Tawara, Taira Tsuchiya, Tetsuji Ogawa, and Tetsunori Kobayashi,
    "Speaker Feature Extraction using Adversarial Training,"
    In Proceedings of 2018 Spring Meeting of Acoustic Society of Japan (ASJ 2018), pp.141–144, March 2018.
    
12. 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 2018 Spring Meeting of Acoustic Society of Japan (ASJ 2018), pp.9–12, March 2018.
    

Grants

1. ACT-X, JST [link]
2. JSPS Research Fellowship for Young Scientists (DC1), JSPS [link]
3. AIP Challenge Program, JST (Aug. 2019 – Mar. 2020)

Awards

1. Best Student Presentation Award, IBIS2022, 2022 [link]
2. Outstanding Presentation Award, IBIS2020, 2020 [link]
3. Travel Award, NeurIPS 2020
4. UTokyo Toyota-Dwango AI Scholarship (Apr. 2020 – Mar. 2021)
5. UTokyo Toyota-Dwango AI Scholarship (Apr. 2019 – Mar. 2020)
6. JEES-Softbank AI Scholarship (Apr. 2019 – Mar. 2020)
7. Department Award, Waseda University, 2018

Professional Activities (Reviewer)

• NeurIPS2021, NeurIPS2022

Contact

• mail: scse.taira [at] gmail.com