Kaito Ariu - My portal

Profile Information

Affiliation: Research Scientist, AI Lab, Reinforcement Learning, CyberAgent

Degree: Ph.D. (Electrical Engineering)(Nov, 2023, KTH Royal Institute of Technology)

Contact information: kaito_ariucyberagent.co.jp
Researcher number: 80984286
ORCID iD: https://orcid.org/0000-0001-6286-9906
J-GLOBAL ID: 202301001862308187
researchmap Member ID: R000052246

Research History

2021 - Present

Research Scientist, AI Lab, CyberAgent, Inc.

Education

2018 - 2023

Division of Decision and Control Systems, EECS, Doctoral Program, KTH Royal Institute of Technology

Committee Memberships

Awards

Mar, 2025

言語処理学会第31回年次大会優秀賞, テキスト生成における最小ベイズリスク復号の理論的な理解に向けて

市原有生希, 陣内佑, 蟻生開人, 森村哲郎, 内部英治
Nov, 2023

Top Reviewer NeurIPS 2023, NeurIPS

Kaito Ariu
2018

Iizuka Takeshi Scholarship Foundation

Kaito Ariu
Sep, 2017

The Nakajima Foundation Scholarship for study abroad

Kaito Ariu
Apr, 2017

JSPS Research Fellowships for Young Scientists DC1

Kaito Ariu
2017

Designated as a member of Masayoshi Son (Founder of Softbank) Foundation

Kaito Ariu
Oct, 2016

Pre-SEUT scholarship

Kaito Ariu
May, 2016

Exemption from Repayment of JASSO Scholarship Loan

Kaito Ariu
Feb, 2016

日本学生支援機構第二種奨学金(短期留学) 採用

Kaito Ariu
Feb, 2016

1st Place Paper Award for Young Scientists, 59th Symposium on Space Science and Technology

Kaito Ariu
Feb, 2016

Tobitate Japan overseas scholarship program

Kaito Ariu
2016

Advances in Space Research - Most Downloaded Article in the last 90 days, A dimensionless relative trajectory estimation algorithm for autonomous imaging of a small astronomical body in a close distance flyby

Kaito Ariu
Oct, 2015

NEC C&C Foundation grants for the prentation at an international conference

Kaito Ariu
Oct, 2015

Selected member of the Global Leader Program for Social Design and Management

Kaito Ariu
Sep, 2015

Selected member of a Workshop for Interdisciplinary Global Engineers Program to visit MIT

Kaito Ariu
May, 2015

Distinction Award of Hybrid Art, Prix Ars Electronica 2015, ARTSAT1:INVADER team

ARTSAT INVADER team
Mar, 2015

The University of Tokyo President's Award for PROCYON mission, The University of Tokyo

PROCYON project team
Mar, 2015

Japan Society for Aeronautical and Space Sciences Student Award (Graduated with highest honors)

Kaito Ariu

Papers

Global Behavior of Learning Dynamics in Zero-Sum Games with Memory Asymmetry

Yuma Fujimoto, Kaito Ariu, Kenshi Abe

AAMAS (full paper), May, 2025 Peer-reviewed
Nash Equilibrium and Learning Dynamics in Three-Player Matching $m$-Action Games

Yuma Fujimoto, Kaito Ariu, Kenshi Abe

AAMAS (extended abstract), May, 2025 Peer-reviewed
Boosting Perturbed Gradient Ascent for Last-Iterate Convergence in Games

Kenshi Abe, Mitsuki Sakamoto, Kaito Ariu, Atsushi Iwasaki

ICLR, Apr, 2025 Peer-reviewed
Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment

Yuu Jinnai, Tetsuro Morimura, Kaito Ariu, Kenshi Abe

NAACL (main), Apr, 2025 Peer-reviewed
Efficient Creative Selection in Online Advertising using Top-Two Thompson Sampling

Daiki Katsuragawa, Yusuke Kaneko, Kaito Ariu, Kenshi Abe

WSDM (Industry Day), Mar, 2025 Peer-reviewed
Synchronization behind Learning in Periodic Zero-Sum Games Triggers Divergence from Nash equilibrium

Yuma Fujimoto, Kaito Ariu, Kenshi Abe

AAAI, Feb, 2025 Peer-reviewed
Evaluation of Best-of-N Sampling Strategies for Language Model Alignment

Yuki Ichihara, Yuu Jinnai, Tetsuro Morimura, Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Eiji Uchibe

Transactions on Machine Learning Research, Jan, 2025 Peer-reviewed
A Comment on “Adaptive Treatment Assignment in Experiments for Policy Choice” (2021)

Kaito Ariu, Masahiro Kato, Junpei Komiyama, Kenichiro McAlinn, Chao Qin

Econometrica, Jan, 2025 Peer-reviewedLead author
Filtered Direct Preference Optimization

Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai, Kenshi Abe, Kaito Ariu

EMNLP (main), Nov, 2024 Peer-reviewed
Last Iterate Convergence in Monotone Mean Field Games

Noboru Isobe, Kenshi Abe, Kaito Ariu

Oct 7, 2024
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding

Yuu Jinnai, Kaito Ariu

ACL (Findings), Aug, 2024 Peer-reviewed
Matroid Semi-Bandits in Sublinear Time

ICML, Jul, 2024 Peer-reviewed
Model-Based Minimum Bayes Risk Decoding

Yuu Jinnai, Tetsuro Morimura, Ukyo Honda, Kaito Ariu, Kenshi Abe

ICML, Jul, 2024 Peer-reviewed
On Universally Optimal Algorithms for A/B Testing

Po-An Wang, Kaito Ariu, Alexandre Proutiere

ICML, Jul, 2024 Peer-reviewed
Adaptively Perturbed Mirror Descent for Learning in Games

Kenshi Abe, Kaito Ariu, Mitsuki Sakamoto, Atsushi Iwasaki

ICML, Jul, 2024 Peer-reviewed
Optimal Clustering from Noisy Binary Feedback

Kaito Ariu, Jungseul Ok, Alexandre Proutiere, Se-Young Yun

Machine Learning, Feb 16, 2024 Peer-reviewedLead author
Return-Aligned Decision Transformer

Tsunehiko Tanaka, Kenshi Abe, Kaito Ariu, Tetsuro Morimura, Edgar Simo-Serra

Feb 6, 2024
Memory Asymmetry Creates Heteroclinic Orbits to Nash Equilibrium in Learning in Zero-Sum Games

Yuma Fujimoto, Kaito Ariu, Kenshi Abe

AAAI, Feb, 2024 Peer-reviewed
Rate-Optimal Bayesian Simple Regret in Best Arm Identification

Junpei Komiyama, Kaito Ariu, Masahiro Kato, Chao Qin

Mathematics of Operations Research, Aug 25, 2023 Peer-reviewed
Instance-Optimal Cluster Recovery in the Labeled Stochastic Block Model

Kaito Ariu, Alexandre Proutiere, Se-Young Yun

Jun 18, 2023 Lead author

Misc.

【採択論文紹介】A/Bテストにおいて最適な手法は何か？ (ICML2024)

Kaito Ariu

Jun, 2024

Research Projects

ミニマックス最適化で拓く最適方策探索手法の構築

Apr, 2025 - Mar, 2031

Kaito Ariu
本質的な構造を活かした大規模逐次的意思決定手法の構築

日本学術振興会 2023年度研究活動スタート支援, 2023 - 2025

蟻生開人
共分散行列による不確定性の記述が過大な制御誤差を生む対象の制御手法の構築

科学研究費助成事業特別研究員奨励費, 特別研究員奨励費, 日本学術振興会, Apr, 2017 - Mar, 2020

蟻生開人

Media Coverage

AI Lab、深層学習分野のトップカンファレンス「ICLR 2025」にて2本の論文採択

https://www.cyberagent.co.jp/news/detail/id=31574, Mar, 2025 Internet
AI Lab、自然言語処理分野のトップカンファレンス「NAACL 2025」にて3本の論文採択

https://www.cyberagent.co.jp/news/detail/id=31509, Mar, 2025 Internet
AI Lab、人工知能分野のトップカンファレンス「AAAI 2025」にて3本の論文採択

https://www.cyberagent.co.jp/news/detail/id=31431, Feb, 2025 Internet
ドコモと共同設立した「株式会社Prism Partner」への技術提供に関する論文が、Web分野のトップカンファレンス「WSDM 2025」に採択

https://www.cyberagent.co.jp/news/detail/id=31406, Feb, 2025 Internet
AI Lab、マルチエージェント分野のトップカンファレンス「AAMAS 2025」にて主著論文採択

https://www.cyberagent.co.jp/news/detail/id=31410, Feb, 2025 Internet
AI Lab、自然言語処理分野のトップカンファレンス「EMNLP 2024」にて論文採択

https://www.cyberagent.co.jp/news/detail/id=30949, Oct, 2024 Internet
AI Lab、自然言語処理分野のトップカンファレンス「ACL 2024」にて3本の論文採択

https://www.cyberagent.co.jp/news/detail/id=30532, Jul, 2024 Internet
AI Lab、機械学習分野のトップカンファレンス「ICML 2024」にて、過去最多となる5本の論文採択

https://www.cyberagent.co.jp/news/detail/id=30359, Jun, 2024 Internet
人工知能分野のトップカンファレンス「AAAI 2024」にて2本の共著論文採択

https://www.cyberagent.co.jp/news/detail/id=29714, Jan, 2024 Internet
AI Lab、さきがけ事業・科学研究費助成事業において2件の研究課題採択

https://www.cyberagent.co.jp/news/detail/id=29499, Nov, 2023 Internet
AI Lab、人工知能分野のトップカンファレンス「IJCAI 2023」にて主著論文採択

https://www.cyberagent.co.jp/news/detail/id=28934, Jun, 2023 Internet
AI Lab、情報検索・推薦システム分野のトップカンファレンス「SIGIR2023」にて3本の主著論文採択

https://www.cyberagent.co.jp/news/detail/id=28884, May, 2023 Internet
AI Lab、機械学習分野のトップカンファレンス「ICML2022」にて論文採択ー高次元情報を用いた逐次的な意思決定手法を提案ー

https://www.cyberagent.co.jp/news/detail/id=27702, 2022 Internet