Breadcrumb navigation

Our Researchers

November 9, 2021

Shinji Ito

Data Mining Technology Group
Data Science Research Labs

Research Domains

  • Research Domains
  • Numerical computing

Publication List

  • Shinji Ito, On Optimal Robustness to Adversarial Corruption in Online Decision Problems, the 35th Annual Conference on Neural Information Processing Systems (NeurIPS), 2021.
  • Shinji Ito, Hybrid Regret Bounds for Combinatorial Semi-Bandits and Adversarial Linear Bandits, the 35th Annual Conference on Neural Information Processing Systems (NeurIPS), 2021.
  • Shinji Ito, Parameter-Free Multi-Armed Bandit Algorithms with Hybrid Data-Dependent Regret Bounds, the Thirty Fourth Conference on Learning Theory (COLT), 2021.
  • Kei Takemura, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi, A Parameter-Free Algorithm for Misspecified Linear Contextual Bandits, the 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
  • Tatsuya Matsuoka, Shinji Ito, Naoto Ohsaka, Tracking Regret Bounds for Online Submodular Optimization, the 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.
  • 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, the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021.
  • Shinji Ito, A Tight Lower Bound and Efficient Reduction for Swap Regret, the 34th Annual Conference on Neural Information Processing Systems (NeurIPS), 2020. # Selected for spotlight presentation
  • Shinji Ito, Shuichi Hirahara, Tasuku Soma, Yuichi Yoshida, Tight First- and Second-Order Regret Bounds for Adversarial Linear Bandits, the 34th Annual Conference on Neural Information Processing Systems (NeurIPS), 2020. # Selected for spotlight presentation
  • Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi, Delay and Cooperation in Nonstochastic Linear Bandits, the 34th Annual Conference on Neural Information Processing Systems (NeurIPS), 2020. # Selected for spotlight presentation
  • Shinji Ito, An Optimal Algorithm for Bandit Convex Optimization with Strongly-Convex and Smooth Loss, The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
  • Kei Takemura, Shinji Ito, An Arm-Wise Randomization Approach to Combinatorial Linear Semi-Bandits, 2019 IEEE International Conference on Data Mining (ICDM), 2019.
  • Shinji Ito, Submodular Function Minimization with Noisy Evaluation Oracle, 33rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2019.
  • 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, 33rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2019.
  • Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi, Improved Regret Bounds for Bandit Combinatorial Optimization, 33rd Annual Conference on Neural Information Processing Systems (NeurIPS), 2019.
  • 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, 32nd Annual Conference on Neural Information Processing Systems (NIPS), 2018.
  • Shinji Ito, Akihiro Yabe, Ryohei Fujimaki Unbiased Objective Estimation in Predictive Optimization The 35th International Conference on Machine Learning (ICML 2018)
  • Akihiro Yabe, Daisuke Hatano, Hanna Sumita, Shinji Ito, Naonori Kakimura, Takuro Fukunaga, Ken-ichi Kawarabayashi. Causal Bandit with Propagating Inference, The 35th International Conference on Machine Learning (ICML 2018)
  • Shinji Ito and Yuji Nakatsukasa, Stable polefinding and rational least-squares fitting via eigenvalues. Numerische Mathematik 139(3): 633-682 (2018)
  • Shinji Ito, Daisuke Hatano, Hanna Sumita, Akihiro Yabe, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi, Online Regression with Partial Information: Generalization and Linear Projection, International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
  • Masafumi Oyamada, Jianquan Liu, Shinji Ito, Kazuyo Narita, Takuya Araki, Hiroyuki Kitagawa, "Compressed Vector Set: A Fast and Space-Efficient Data Mining Framework", Journal of Information Processing , Vol.26, pp. 416-426, 2018.
  • 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, Thirty-first Annual Conference on Neural Information Processing Systems (NIPS), 2017
  • Shinji Ito and Ryohei Fujimaki, Optimization Beyond Prediction: Prescriptive Price Optimization, SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2017
  • A. Yabe, S. Ito and R. Fujimaki, Robust Quadratic Programming for Price Optimization, International Joint Conference on Artificial Intelligence (IJCAI), 2017
  • Shinji Ito, Ryohei Fujimaki. Large-Scale Price Optimization via Network Flow. In Advances in Neural Information Processing (NIPS), 2016. # Selected for NIPS oral presentation (top 2% submission)
  • S. Ito, K. Aishima, T. Nara, M. Sugihara, Orthogonal polynomial approach to estimation of poles of rational functions from data on open curves, J. Comput. Appl. Math., 274 (2015) 326-345.
  • S. Ito, K. Murota. An Algorithm for the Generalized Eigenvalue Problem for Nonsquare Matrix Pencils by Minimal Perturbation Approach. SIAM J. Matrix Anal. Appl., 37(1):409-419, 2016.

Awards/Prizes

  • March, 2020 Dean’s Award from Graduate School of Information Science and Technology,
    University of Tokyo

Memberships

  • The Japan Society for Industrial and Applied Mathematics
  • The Operations Research Society of Japan

Conference presentation

  • Shinji Ito, Kazuo Murota, An algorithm for solving the generalized eigenvalue problem for non-square matrices using a minimal perturbation approach, International Workshop on Eigenvalue Problems: Algorithms; Software and Applications, in Petascale Computing(EPASA2014)(poster session), Tsukuba, Japan, March 2014.

Biography

  • March 2013: B.S. in Department of Mathematical Engineering and Information Physics, The University of Tokyo
  • March 2015: M.S. in Graduate School of Information Science and Technology, The University of Tokyo
  • April 2018: Ph.D. Student at Department of Mathematical Informatics, Graduate School of Information Science and Technology, The University of Tokyo
  • March 2020: Ph.D. in Graduate School of Information Science and Technology, The University of Tokyo