Honda Junya

ホンダジュンヤ | Honda Junya

Affiliation and department：
Job title：准教授
Research theme for competitive and other funds (7)：

2021 - 2024 バンディット問題における最適性達成のためのランダム方策の発展と解析
2018 - 2021 Construction of knowledge discovery algorithms based on information theoretic methods
2016 - 2018 確率モデルに基づいた結晶構造の学習および推定法の確立
2014 - 2016 効率的な材料探索のための実験計画法の開発
2013 - 2015 多腕バンディット問題における最適戦略の構成と発展

Show all

Papers (57)：

Jongyeong Lee, Junya Honda, Shinji Ito, Min-hwan Oh. Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds. COLT. 2024. 3375-3430
Shinji Ito, Taira Tsuchiya, Junya Honda. Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds. COLT. 2024. 2522-2563
Kentaro Matsuura, Kentaro Sakamaki, Junya Honda, Takashi Sozu. Optimal dose escalation methods using deep reinforcement learning in phase I oncology trials. Journal of biopharmaceutical statistics. 2023. 1-14
Taira Tsuchiya, Shinji Ito, Junya Honda. Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds. NeurIPS. 2023
Jongyeong Lee, Junya Honda, Chao-Kai Chiang, Masashi Sugiyama. Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits. ICML. 2023. 18810-18851

ｍore...

MISC (5)：

田畑公次, 中村篤祥, 本多淳也, 小松崎民樹. Bad Arm Existence Checking Algorithms with Small Sample Complexity. 人工知能基本問題研究会. 2018. 106. 94-99
TSUCHIHASHI Masato, YAMAMOTO Hirosuke, HONDA Junya. Construction of Almost Instantaneous FV codes based on Integer Programming. IEICE technical report. Information theory. 2014. 114. 138. 1-6
HONDA Junya, YAMAMOTO Hirosuke. Variable Length Coding of Asymmetric Channels using a Homophonic Code. IEICE technical report. Information theory. 2012. 112. 124. 109-114
HONDA Junya, TAKEMURA Akimichi. On a Non-asymptotic Analysis Using Large Deviation Principles in the Multiarmed Bandit Problem. 2012. 112. 83. 65-72
HONDA Junya, MIYAKE Shigeki, YAMAMOTO Hirosuke, MARUYAMA Mitsuru. Source Coding with LDPC Code using Linear Programming. IEICE technical report. 2008. 108. 158. 27-32

Books (1)：

バンディット問題の理論とアルゴリズム = Theory and algorithms for bandit problems
講談社 2016 ISBN:9784061529175

Education (1)：

2010 - 2013 The University of Tokyo Graduate School of Frontier Sciences Department of Complexity Science and Engineering

Professional career (1)：

Work history (3)：

2021/01 - 現在 Kyoto University Department of Systems Science, Graduate School of Informatics Associate Professor
2017/01 - 2020/12 The University of Tokyo Department of Complexity Science and Engineering, Graduate School of Frontier Sciences Lecturer
2013/03 - 2016/12 The University of Tokyo Department of Complexity Science and Engineering, Graduate School of Frontier Sciences Research Associate

Awards (4)：

2023 - 情報論的学習理論と機械学習研究会 IBISML研究会賞
2017 - 人工知能学会全国大会優秀賞(口頭発表部門)
2016 - IEEE IT Society Japan Chapter Young Researcher Best Paper Award in ISITA 2016
2011 - 情報理論とその応用学会 SITA 奨励賞

※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page