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

Studies of models and algorithms in machine learning via submodular optimization

Research Project

Project/Area Number 16H06676
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeSingle-year Grants
Research Field Mathematical informatics
Research InstitutionThe University of Tokyo

Principal Investigator

Soma Tasuku  東京大学, 大学院情報理工学系研究科, 助教 (90784827)

Project Period (FY) 2016-08-26 – 2018-03-31
Project Status Completed (Fiscal Year 2017)
Budget Amount *help
¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords組合せ最適化 / 機械学習 / アルゴリズム
Outline of Final Research Achievements

Recently, submodular optimization -- a branch of combinatorial optimization -- has attracted interests in the machine learning community. In this project, we studied submodular optimization and its applications to machine learning, and obtained the following results:
1. We developed new approximation guarantee based on the concept of discrete convexity, which improves previous approaches based on the concept of curvature.
2. For dictionary learning (a problem studied in compressed sensing and machine learning), we devise a new combinatorial algorithm.

Report

(3 results)
  • 2017 Annual Research Report   Final Research Report ( PDF )
  • 2016 Annual Research Report
  • Research Products

    (11 results)

All 2018 2017

All Journal Article (4 results) (of which Peer Reviewed: 3 results,  Open Access: 1 results) Presentation (7 results) (of which Int'l Joint Research: 3 results,  Invited: 1 results)

  • [Journal Article] A New Approximation Guarantee for Monotone Submodular Function Maximization via Discrete Convexity2018

    • Author(s)
      Tasuku Soma and Yuichi Yoshida
    • Journal Title

      Proceedings of the 45th International Colloquium on Automata, Languages, and Programming (ICALP)

      Volume: -

    • Related Report
      2017 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 整数格子点上の劣モジュラ最大化と近似アルゴリズム2018

    • Author(s)
      相馬輔
    • Journal Title

      オペレーションズ・リサーチ

      Volume: 63 Pages: 36-42

    • Related Report
      2017 Annual Research Report
    • Open Access
  • [Journal Article] Regret Ratio Minimization in Multi-objective Submodular Function Maximization2017

    • Author(s)
      Tasuku Soma and Yuichi Yoshida
    • Journal Title

      Proceedings of the 31st AAAI Conference on Artificial Inteligence

      Volume: -

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Non-monotone DR-Submodular Function Maximization2017

    • Author(s)
      Tasuku Soma and Yuichi Yoshida
    • Journal Title

      Proceedings of the 31st AAAI Conference on Artificial Inteligence

      Volume: -

    • Related Report
      2016 Annual Research Report
    • Peer Reviewed
  • [Presentation] 離散凸性による劣モジュラ最大化の近似比保証2018

    • Author(s)
      相馬輔,吉田悠一
    • Organizer
      日本オペレーションズ・リサーチ学会 「離散アルゴリズムの応用と理論」研究部会
    • Related Report
      2017 Annual Research Report
  • [Presentation] Regret Ratio Minimization in Multi-objective Submodular Function Maximization2017

    • Author(s)
      Tasuku Soma and Yuichi Yoshida
    • Organizer
      The 10th Japanese-Hungarian Symposium on Discrete Mathematics and Its Applications
    • Related Report
      2017 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 離散凸性による劣モジュラ最大化の近似比保証2017

    • Author(s)
      相馬輔,吉田悠一
    • Organizer
      Japanese Center for Combinatorics and its Applications Japanese Conference on Combinatorics and its Applications
    • Related Report
      2017 Annual Research Report
  • [Presentation] 整数格子点上の劣モジュラ最大化と近似アルゴリズム2017

    • Author(s)
      相馬輔
    • Organizer
      第29回 RAMPシンポジウム
    • Related Report
      2017 Annual Research Report
    • Invited
  • [Presentation] Regret Ratio Minimization in Multi-objective Submodular Function Maximization2017

    • Author(s)
      Tasuku Soma and Yuichi Yoshida
    • Organizer
      The 31st AAAI Conference on Artificial Inteligence
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Non-monotone DR-Submodular Function Maximization2017

    • Author(s)
      Tasuku Soma and Yuichi Yoshida
    • Organizer
      The 31st AAAI Conference on Artificial Inteligence
    • Related Report
      2016 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 相馬輔,吉田悠一2017

    • Author(s)
      多目的劣モジュラ最大化に対するリグレット比最小化
    • Organizer
      日本オペレーションズリサーチ学会春季研究発表会
    • Related Report
      2016 Annual Research Report

URL: 

Published: 2016-09-02   Modified: 2019-03-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi