• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Theory Deepening for Practical Applications of Bandit Problem Policies

Research Project

Project/Area Number 19H04161
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Review Section Basic Section 61030:Intelligent informatics-related
Research InstitutionHokkaido University

Principal Investigator

Nakamura Atsuyoshi  北海道大学, 情報科学研究院, 教授 (50344487)

Co-Investigator(Kenkyū-buntansha) 田畑 公次  北海道大学, 電子科学研究所, 准教授 (20814445)
工藤 峰一  北海道大学, 情報科学研究院, 教授 (60205101)
Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥9,750,000 (Direct Cost: ¥7,500,000、Indirect Cost: ¥2,250,000)
Fiscal Year 2022: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2021: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Keywordsバンディット問題 / オンライン学習 / バンディット / 分類バンディット問題 / 敵対的バンディット / 最適腕識別 / アルゴリズム / 大規模探索 / 敵対的バンディット問題 / 敵対的バンデット
Outline of Research at the Start

探索と知識利用のトレードオフを扱うバンディット問題は、オンライン最適化の様々な問題に応用できるポテンシャルをもっている。本研究は、バンディット問題の方策を実用化という観点から見直し、一般には情報量的または計算量的に困難だとされる問題をヒューリスティクスで解決するのではなく、現実的な制約を課して理論的に精度と効率性を保証する方策を開発することにより、バンディット問題の理論を深化させ、実用化を加速する。敵対的バンディット問題の方策およびモンテカルロ木探索を用いた大規模空間探索において、アルゴリズムの実用化のための定式化の見直しを行い、精度・効率性が理論的に保証された実用的なアルゴリズムを開発する。

Outline of Final Research Achievements

In both adversarial and stochastic bandit settings, we formalized problems that are inspired by practical utility, proposed their efficient and high-performance solution algorithms, and evaluated them theoretically and experimentally. In the adversarial bandit setting, we developed an asymptotically optimal algorithm under the condition that at least one arm does not suffer any loss. In the stochastic setting, we formalized the classification bandit problem, in which the player decides whether the number of arms with their expected rewards at least a given threshold is at least a given threshold or not by drawing arms iteratively, and developed the P-tracking algorithm that is efficient and asymptotically optimal. These results are published in major peer-reviewed international journals and conference proceedings.

Academic Significance and Societal Importance of the Research Achievements

バンディット問題のアルゴリズムは、昔から効率的な治験を行うために研究され、現代ではインターネット広告配信、推薦システム、A/Bテストなどに用いられている。基本的に、能動的なサンプリングを行なって効率的に情報を得る方法の研究であり、様々な応用の可能性を秘めている。開発した分類バンディットアルゴリズムは、ラマン分光によるインタラクティブ計測による病理診断の高速化にも用いいることも可能であり、今後様々な分野の応用に発展することが期待される。

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Annual Research Report
  • 2020 Annual Research Report
  • 2019 Annual Research Report
  • Research Products

    (19 results)

All 2023 2022 2021 2020 2019 Other

All Int'l Joint Research (1 results) Journal Article (12 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 10 results,  Open Access: 7 results) Presentation (6 results) (of which Int'l Joint Research: 1 results)

  • [Int'l Joint Research] UC SANTA CRUZ(米国)

    • Related Report
      2019 Annual Research Report
  • [Journal Article] 単調増加制約のあるレベルセット推定2023

    • Author(s)
      田畑 公次、中村 篤祥、高見 亮佑、Joshua Arenson、和田 弥生、Walker Peterson、合田 圭介、園下 将大、小松崎 民樹
    • Journal Title

      JSAI Technical Report, SIG-FPAI

      Volume: 124 Issue: 0 Pages: 25-30

    • DOI

      10.11517/jsaifpai.124.0_25

    • ISSN
      2436-4584
    • Year and Date
      2023-03-06
    • Related Report
      2022 Annual Research Report
  • [Journal Article] 与えられたデータに無矛盾なコンパクトな多出力二分決定グラフの質問学習2023

    • Author(s)
      中村 篤祥
    • Journal Title

      JSAI Technical Report, SIG-FPAI

      Volume: 123 Issue: 0 Pages: 31-36

    • DOI

      10.11517/jsaifpai.123.0_31

    • ISSN
      2436-4584
    • Year and Date
      2023-01-05
    • Related Report
      2022 Annual Research Report
  • [Journal Article] Posterior Tracking Algorithm for Classification Bandits2023

    • Author(s)
      Koji Tabata, Junpei Komiyama, Atsuyoshi Nakamura, Tamiki Komatsuzaki
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: 206 Pages: 10994-11022

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Propagation graph estimation from individuals’ time series of observed states2022

    • Author(s)
      Hayashi Tatsuya、Nakamura Atsuyoshi
    • Journal Title

      Scientific Reports

      Volume: 12 Issue: 1 Pages: 6078-6078

    • DOI

      10.1038/s41598-022-10031-3

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Efficient alignment-based average delay time estimation in fluctuating delayed propagation2022

    • Author(s)
      Nakamura Atsuyoshi、Hayashi Tatsuya
    • Journal Title

      Array

      Volume: 15 Pages: 100240-100240

    • DOI

      10.1016/j.array.2022.100240

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] An Explainable Recommendation Based on Acyclic Paths in an Edge-Colored Graph2022

    • Author(s)
      Chinone Kosuke、Nakamura Atsuyoshi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 13151 Pages: 40-52

    • DOI

      10.1007/978-3-030-97546-3_4

    • ISBN
      9783030975456, 9783030975463
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Classification Bandits: Classification Using Expected Rewards as Imperfect Discriminators2021

    • Author(s)
      Tabata Koji、Nakumura Atsuyoshi、Komatsuzaki Tamiki
    • Journal Title

      Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Workshop on Machine Learning for MEasurement INformatics

      Volume: - Pages: 57-69

    • DOI

      10.1007/978-3-030-75015-2_6

    • ISBN
      9783030750145, 9783030750152
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Minor-embedding heuristics for large-scale annealing processors with sparse hardware graphs of up to 102,400 nodes2021

    • Author(s)
      Sugie Y, Yoshida Y, Mertig N, Takemoto T, Teramoto H, Nakamura A, Takigawa I, Minato S, Yamaoka M, Komatsuzaki T
    • Journal Title

      Soft Computing

      Volume: 25(3) Issue: 3 Pages: 1731-1749

    • DOI

      10.1007/s00500-020-05502-6

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Data-Dependent Conversion to a Compact Integer-Weighted Representation of a Weighted Voting Classifier.2020

    • Author(s)
      Mitsuki Maekawa, Atsuyoshi Nakamura, Mineichi Kudo
    • Journal Title

      Proceedings of Machine Learning Research

      Volume: 129 Pages: 241-256

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Feature selection as Monte-Carlo Search in Growing Single Rooted Directed Acyclic Graph by Best Leaf Identification2019

    • Author(s)
      Pelissier A, Nakamura A, Tabata K
    • Journal Title

      SIAM International Conference on Data Mining(SDM2019)

      Volume: - Pages: 450-458

    • DOI

      10.1137/1.9781611975673.51

    • ISBN
      9781611975673
    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Mistake bounds on the noise-free multi-armed bandit game2019

    • Author(s)
      Nakamura Atsuyoshi、Helmbold David P.、Warmuth Manfred K.
    • Journal Title

      Information and Computation

      Volume: 269 Pages: 104453-104453

    • DOI

      10.1016/j.ic.2019.104453

    • NAID

      120007173927

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] A bad arm existence checking problem: How to utilize asymmetric problem structure?2019

    • Author(s)
      Tabata Koji、Nakamura Atsuyoshi、Honda Junya、Komatsuzaki Tamiki
    • Journal Title

      Machine Learning

      Volume: 109 Issue: 2 Pages: 327-372

    • DOI

      10.1007/s10994-019-05854-7

    • Related Report
      2019 Annual Research Report
    • Peer Reviewed / Open Access
  • [Presentation] データ分布のクラスタ構造適合による転移学習2022

    • Author(s)
      Gong Linghua, 中村篤祥
    • Organizer
      第14回データ工学と情報マネジメントに関するフォーラム
    • Related Report
      2021 Annual Research Report
  • [Presentation] ユーザ-アイテム間の関係パスによる複数の説明が可能な推薦2021

    • Author(s)
      茅根宏介, 中村篤祥
    • Organizer
      第24回情報論的学習理論ワークショップ
    • Related Report
      2021 Annual Research Report
  • [Presentation] 決定森の分岐条件の共有化の効果と応用2020

    • Author(s)
      中村 篤祥、櫻田 健斗
    • Organizer
      人工知能学会全国大会
    • Related Report
      2020 Annual Research Report
  • [Presentation] バンディット問題の方策を用いたモンテカルロ木探索による最適属性集合 探索2019

    • Author(s)
      中村篤祥, ペリシエ オレリアン, 田畑 公次, 小松崎 民樹
    • Organizer
      第19回日本蛋白質科学会年会第71回日本細胞生物学会大会合同年次大会
    • Related Report
      2019 Annual Research Report
  • [Presentation] モンテカルロ木特徴探索に基づく非線形グラフ分類回帰2019

    • Author(s)
      白川稜, 中村篤祥, 工藤峰一
    • Organizer
      第22回情報論的学習理論ワークショップ
    • Related Report
      2019 Annual Research Report
  • [Presentation] _Learning a Nonlinear Model of Subgraph Features Using Monte Carlo Tree Search2019

    • Author(s)
      Ryo Shirakawa, Atsuyoshi Nakamura, Mineichi Kudo
    • Organizer
      ACML 2019 Workshop on Statistics & Machine Learning Researchers in Japan
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi