Shinji Ito

Profile Information

Affiliation: Associate professor, The University of Tokyo

Degree: 博士(情報理工学)(Mar, 2020, 東京大学)

Contact information: shinjimist.i.u-tokyo.ac.jp
J-GLOBAL ID: 201801001063967895
researchmap Member ID: B000311435

The email address (i-shinji@nec.com) used until March 2024 is no longer available.
I am now using the email address shown on this page.

Research Areas

Informatics / Information theory /

Research History

Apr, 2024 - Present

Associate Professor, The Graduate School of Information Science and Technology Department of Mathematical Informatics, The University of Tokyo
Oct, 2023 - Present

Team Leader, AIP, Sequential Decision-Making Team, RIKEN
Apr, 2015 - Mar, 2024

NEC

Education

Apr, 2018 - Mar, 2020

Department of Mathematical Informatics, The Graduate School of Information Science and Technology, The University of Tokyo
Apr, 2013 - Mar, 2015

Department of Mathematical Informatics, The Graduate School of Information Science and Technology, The University of Tokyo
Apr, 2011 - Mar, 2013

Department of Mathematical Engineering and Information Physics, The Faculty of Engineering, The University of Tokyo

Awards

Mar, 2022

第24回情報論的学習理論ワークショップ(IBIS2021) 優秀発表賞

伊藤伸志
Mar, 2020

研究科長賞, 東京大学大学院情報理工学系研究科

伊藤伸志
Jun, 2018

日本オペレーションズ・リサーチ学会研究部会「最適化とその応用」優秀発表賞

伊藤伸志
Jan, 2018

IBIS2017 ベストプレゼンテーション賞

伊藤伸志
Mar, 2017

人工知能学会全国大会優秀賞

伊藤伸志
Nov, 2016

IBIS2016 ベストプレゼンテーション賞

伊藤伸志
Aug, 2014

若手優秀講演賞, 日本応用数理学会

伊藤伸志
May, 2014

最優秀発表賞, 日本オペレーションズ・リサーチ学会「最適化の理論と応用」研究部会

伊藤伸志

Papers

Active model selection: A variance minimization approach

Satoshi Hara, Mitsuru Matsuura, Junya Honda, Shinji Ito

Machine Learning, Nov 21, 2024 Peer-reviewed
Online $\textrm{L}^{\natural }$-Convex Minimization.

Ken Yokoyama, Shinji Ito, Tatsuya Matsuoka, Kei Kimura, Makoto Yokoo

Machine Learning and Knowledge Discovery in Databases. Research Track - European Conference, 319-336, 2024 Peer-reviewed
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets.

Taira Tsuchiya, Shinji Ito

NeurIPS, 2024 Peer-reviewed
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, Shinji Ito

NeurIPS, 2024 Peer-reviewed
On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice.

Shinji Ito

NeurIPS, 2024 Peer-reviewedLead authorCorresponding author
Learning with Posterior Sampling for Revenue Management under Time-varying Demand.

Kazuma Shimizu, Junya Honda, Shinji Ito, Shinji Nakadai

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence(IJCAI), 4911-4919, 2024 Peer-reviewed
Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring.

Taira Tsuchiya, Shinji Ito, Junya Honda

Forty-first International Conference on Machine Learning(ICML), 2024 Peer-reviewed
Best-of-Both-Worlds Linear Contextual Bandits.

Masahiro Kato, Shinji Ito

Transactions on Machine Learning Research, 2024, 2024 Peer-reviewed
Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds.

Jongyeong Lee, Junya Honda, Shinji Ito, Min-hwan Oh

COLT, 3375-3430, 2024 Peer-reviewed
Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds.

Shinji Ito, Taira Tsuchiya, Junya Honda

COLT, 2522-2563, 2024 Peer-reviewedLead authorCorresponding author
New Classes of the Greedy-Applicable Arm Feature Distributions in the Sparse Linear Bandit Problem.

Koji Ichikawa, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

AAAI, 12708-12716, 2024 Peer-reviewed
Maximization of Minimum Weighted Hamming Distance between Set Pairs.

Tatsuya Matsuoka, Shinji Ito

Asian Conference on Machine Learning(ACML), 895-910, 2023 Peer-reviewed
New classes of the greedy-applicable arm feature distributions in the sparse linear bandit problem.

Koji Ichikawa, Shinji Ito, Daisuke Hatano, Hanna Sumita, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

CoRR, abs/2312.12400, 2023
Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds.

Shinji Ito, Kei Takemura

COLT, 2653-2677, 2023 Peer-reviewedLead authorCorresponding author
An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits

Shinji Ito, Kei Takemura

NeurIPS, 2023 Peer-reviewedLead authorCorresponding author
Bandit Task Assignment with Unknown Processing Time

Shinji Ito, Daisuke Hatano, Hanna Sumita, Kei Takemura, Takuro Fukunaga, Naonori Kakimura, Ken-ichi Kawarabayashi

NeurIPS, 2023 Peer-reviewedLead authorCorresponding author
Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds

Taira Tsuchiya, Shinji Ito, Junya Honda

NeurIPS, 2023 Peer-reviewed
Further Adaptive Best-of-Both-Worlds Algorithm for Combinatorial Semi-Bandits.

Taira Tsuchiya, Shinji Ito, Junya Honda

AISTATS, 8117-8144, 2023 Peer-reviewed
Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds.

Shinji Ito, Kei Takemura

Conference on Learning Theory (COLT), 2653-2677, 2023 Peer-reviewedLead authorCorresponding author
Best-of-Both-Worlds Algorithms for Partial Monitoring.

Taira Tsuchiya, Shinji Ito, Junya Honda

ALT, 1484-1515, 2023 Peer-reviewed

Misc.

2-A-4 摂動最小化アプローチによる一般化固有値問題の解法(連続最適化(2))

伊藤伸志, 室田一雄

日本オペレーションズ・リサーチ学会秋季研究発表会アブストラクト集, 2014 168-169, Aug 28, 2014

Presentations

予測に基づく数理計画の現状と課題

伊藤伸志

第40回情報理論とその応用シンポジウムワークショップ（SITA2017）「産業界におけるデータマイニング・人工知能の最先端」, 2017 Invited

Research Projects

部分的フィードバックに基づくオンライン凸最適化

戦略的な研究開発の推進戦略的創造研究推進事業 ACT-I（加速フェーズ）, 科学技術振興機構, Apr, 2020 - Mar, 2022

伊藤伸志
部分的フィードバックに基づくオンライン凸最適化

戦略的な研究開発の推進戦略的創造研究推進事業 ACT-I, 科学技術振興機構, Oct, 2018 - Mar, 2020

伊藤伸志

Profile Information

Research Areas

Research History

Education

Awards

Papers

Misc.

Presentations

Research Projects

Menu

Coauthors