土屋 平 / Taira Tsuchiya

English version is here.

News

• → 最新の News (English page) は主にこちらです．
• Sep 22, 2023: 論文 "Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds," が NeurIPS 2023 に採択されました．プレプリントはこちら．
• Sep 6, 2023: FIT 2023 で最近の best-of-both-worlds 方策の進展についての（短時間の）招待講演をします．スライドはこちら（プレゼンテーション版は こちら）．
  
• May 28, 2021: 論文 "Semi-Supervised Ordinal Regression Based on Empirical Risk Minimization" が Neural Computation に採択されました．
  
• Apr 1, 2021: 指導教員の転任に伴い，京都大学へ転学しました．
• Jan 8, 2021: IBIS2020で優秀発表賞を受賞しました． [link]
• Dec 22, 2020: Toshiba Symposium 2020 で部分観測問題の研究について講演します．スライドはこちら．
  
• Nov 25, 2020: IBIS2020 で口頭発表を行います．
  
• Sep 26, 2020: 論文 "Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring" が NeurIPS2020 に採択されました．
  プレプリントはこちら．
  

論文

Preprints

1. Taira Tsuchiya and Shinji Ito,
   "Fast Rates in Online Convex Optimization by Exploiting the Curvature of Feasible Sets,"
   arXiv:2402.12868, 2024.
   [arXiv]
   
2. Kaito Ito and Taira Tsuchiya,
   "Online Control of Linear Systems with Unbounded and Degenerate Noise,"
   arXiv:2402.10252, 2024.
   [arXiv]
   
3. Taira Tsuchiya, Shinji Ito, and Junya Honda,
   "Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring,"
   arXiv:2402.08321, 2024.
   [arXiv]
   
4. Shinsaku Sakaue, Han Bao, Taira Tsuchiya, Taihei Oki,
   "Online Structured Prediction with Fenchel–Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss,"
   arXiv:2402.08180, 2024.
   [arXiv]
   

Conference Proceedings (peer-reviewed)

1. Yuko Kuroki, Alberto Rumi, Taira Tsuchiya, Fabio Vitale, and Nicolò Cesa-Bianchi,
   "Best-of-Both-Worlds Algorithms for Linear Contextual Bandits,"
   In Proceedings of 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2023), pp.xxx–xxx, 2024.
   [arXiv]
   
2. Taira Tsuchiya, Shinji Ito, and Junya Honda,
   "Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds,"
   In Advances in Neural Information Processing Systems 36 (NeurIPS 2023), pp.xxx–xxx, 2023.
   [arXiv] [slide] [poster]
   
3. 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]
   
4. 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]
   
5. 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)
   [proceeding] [arXiv] [slide]
   
6. 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 (NeurIPS2022), New Orleans, Louisiana, USA, Nov. 28–Dec. 9, 2022)
   [proceeding] [arXiv]
   
7. 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 (NeurIPS2022), New Orleans, Louisiana, USA, Nov. 28–Dec. 9, 2022)
   [proceeding] [arXiv]
   
8. 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]
   
9. 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]
   
10. 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. 土屋 平，伊藤伸志，本多 淳也，
   "オンライン意思決定問題における複数の観測量に同時に依存したリグレット上界を有する FTRL と，それを用いたスパース性依存上界やゲーム依存型上界，両環境最適性の実現,"
   Presented at 26th Information-Based Induction Sciences Workshop (IBIS 2023), Oct. 29– Nov. 1, 2023.
   学生優秀プレゼンテーション賞ファイナリスト [link]
   
2. 土屋 平，
   "組合せ半バンディット問題における適応的 best-of-both-worlds 方策"
   Presented at 第22回情報科学技術フォーラム（FIT2023）, 大阪公立大学　中百舌鳥キャンパス, Sept. 6–8, 2023.
   招待講演
   [slide] [slide (buildwise)]
3. 土屋 平，伊藤伸志，本多 淳也，
   "Best-of-Both-Worlds Algorithms for Partial Monitoring,"
   Presented at 第125回人工知能基本問題研究会（SIG-FPAI）, vo.125, pp.47–53, Aug. 29–30, 2023.
   
4. 本多 淳也，伊藤伸志，土屋 平，
   "バンディット問題における Follow-The-Perturbated-Leader 方策の確率的・ 敵対的最適性について"
   In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop, vol.xxx, no.xx, pp.xxx–xxx, Dec 2022.
   
5. 土屋 平，
   "部分観測問題における Best-of-Both-Worlds 方策"
   数理・情報系研究集会 @ 東京工業大学, Dec. 15, 2022.
   
6. 土屋 平，伊藤伸志，本多 淳也，
   "バンディット問題における Best-of-Both-Worlds 方策の進展：構造的バンディットと分散依存リグレット,"
   Presented at 25th Information-Based Induction Sciences Workshop (IBIS 2022), Nov. 20–23, 2022.
   学生最優秀プレゼンテーション賞 [link]
   
7. 小宮山純平，土屋 平，本多 淳也，
   "固定時間最適腕識別におけるミニマックス最適アルゴリズム,"
   Presented at 25th Information-Based Induction Sciences Workshop (IBIS 2022), Nov. 20–23, 2022.
   
8. Taira Tsuchiya，
   "Towards Practical Algorithms for Online Decision-Making,"
   Seminar at INRIA Lille Scool group, July 8, 2022.
   [slide]
9. Junta Fujinaga, Taira Tsuchiya, and Junya Honda,
   "組合せバンディット問題におけるInformation Directed SamplingのDC緩和について,"
   In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop, vol.122, no.90, pp.129–136, June 2022.
   
10. 土屋 平，
    "部分観測問題におけるThompson抽出,"
    東芝研究開発センターシンポジウム2020 (online), Dec. 22, 2020.
    [slide]
    
11. 土屋 平，本多 淳也，杉山 将，
    "部分観測問題におけるトンプソン抽出アルゴリズムの設計とリグレット解析,"
    Presented at 23rd Information-Based Induction Sciences Workshop (IBIS 2020), Nov. 23–26, 2020.
    優秀発表賞 [link]
    [slide]
    
12. 土屋 平，本多 淳也，杉山 将，
    "経験リスク最小化による半教師付き順序回帰,"
    Presented at 22nd Information-Based Induction Sciences Workshop (IBIS 2019), Nov. 20–23, 2019.
    
13. 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.
    
14. 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.
    
15. 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.
    

研究助成

1. ACT-X「数理・情報のフロンティア」，JST [link]
2. 日本学術振興会特別研究員 (DC1)，JSPS [link]
3. AIPチャレンジプログラム，JST (Aug. 2019 – Mar. 2020)

受賞など

1. 学生優秀プレゼンテーション賞ファイナリスト (Top 7 of approx. 100 student presentations)，IBIS2023，2023 [link]
2. 学生最優秀プレゼンテーション賞 (1st place out of approx. 100 student presentations)，IBIS2022，2022 [link]
3. 優秀発表賞 (Top 5 of 118 all presentations)，IBIS2020，2020 [link]
4. Travel Award, NeurIPS 2020
5. 東京大学トヨタ・ドワンゴ高度人工知能人材奨学金 (Apr. 2020 – Mar. 2021)
6. 東京大学トヨタ・ドワンゴ高度人工知能人材奨学金 (Apr. 2019 – Mar. 2020)
7. JEES・ソフトバンクAI人材育成奨学金 (Apr. 2019 – Mar. 2020)
8. 学科賞，早稲田大学， 2018

Education

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

Work Experiences

1. Oct. 2023 – Present : Assistant Professor, The University of Tokyo
2. Apr. 2021 – Sep. 2023 : Research Fellowship for Young Scientists (DC1), JSPS
3. 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)

Contact

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