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

Development of efficient subgradient methods for convex optimization exploiting the problem structure

Research Project

Project/Area Number 17K12645
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Mathematical informatics
Research InstitutionNihon University

Principal Investigator

ITO Masaru  日本大学, 理工学部, 助手 (90778375)

Project Period (FY) 2017-04-01 – 2021-03-31
Project Status Completed (Fiscal Year 2020)
Budget Amount *help
¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Keywords数理最適化 / 凸最適化問題 / 一次法 / 加速勾配法 / エラーバウンド / 計算量 / 凸最適化 / ヘルダー条件 / 近接点法 / 劣勾配法 / 強凸関数 / 再出発法
Outline of Final Research Achievements

The development of algorithms of solving large-scale convex optimization problems is an important topic which has many applications in machine learning and data mining and so on. This research focused an effective candidate, the first-order methods, for this problem and we established first-order methods which provide efficient performance even if the parameters on the problem structure is unknown in advance. In particular, in the case when the objective function satisfies an error bound condition, we established adaptive first-order methods which ensures nearly-optimal complexity to obtain an approximate solution.

Academic Significance and Societal Importance of the Research Achievements

本研究で確立した一次法のアルゴリズムは、次の三つの観点から実用性・汎用性が高く、幅広い応用が期待される。まず一つ目に、本研究が対象としたエラーバウンドといった問題構造は一般性が高く、この性質が認められる応用問題が数多く存在する。二つ目に、確立したアルゴリズムは、問題構造に関するパラメータが予めわかっていない場合でも、その構造に対して知られている限界の計算量からたかだか対数倍の計算量を保証するため、汎用性が高い。三つ目に、本研究の提案手法は理論保証を持つ計算可能な停止条件を兼ね備えるため、高い実用性が期待される。

Report

(5 results)
  • 2020 Annual Research Report   Final Research Report ( PDF )
  • 2019 Research-status Report
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (9 results)

All 2021 2019 2018

All Journal Article (2 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 2 results) Presentation (7 results) (of which Int'l Joint Research: 3 results)

  • [Journal Article] Nearly Optimal First-Order Methods for Convex Optimization under Gradient Norm Measure: An Adaptive Regularization Approach2021

    • Author(s)
      Masaru Ito、Mituhiro Fukuda
    • Journal Title

      Journal of Optimization Theory and Applications

      Volume: 188 Issue: 3 Pages: 770-804

    • DOI

      10.1007/s10957-020-01806-7

    • NAID

      40022730610

    • Related Report
      2020 Annual Research Report
    • Peer Reviewed
  • [Journal Article] The automorphism group and the non-self-duality of p-cones2019

    • Author(s)
      Masaru Ito, Bruno F. Lourenco
    • Journal Title

      Journal of Mathematical Analysis and Applications

      Volume: 471 Issue: 1-2 Pages: 392-410

    • DOI

      10.1016/j.jmaa.2018.10.081

    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Frank-Wolfe 法における適応的なステップ幅の選択2021

    • Author(s)
      伊藤勝, Zhaosong Lu and Chuan He
    • Organizer
      日本オペレーションズ・リサーチ学会 2021 年春季研究発表会
    • Related Report
      2020 Annual Research Report
  • [Presentation] Nearly optimal first-order method under Holderian error bound: An adaptive proximal point approach2019

    • Author(s)
      Masaru Ito, Mituhiro Fukuda
    • Organizer
      The Sixth International Conference on Continuous Optimization
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] A nearly optimal first order method for convex optimization with an adaption to Holderian error bound condition2019

    • Author(s)
      Masaru Ito, Mituhiro Fukuda
    • Organizer
      International Conference on Nonlinear Analysis and Convex Analysis--International Conference on Optimization: Techniques and Applications
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] 勾配のノルムを停止条件とする準最適な一次法2019

    • Author(s)
      伊藤勝, 福田光浩
    • Organizer
      日本オペレーションズ・リサーチ学会 2019 年春季研究発表会
    • Related Report
      2018 Research-status Report
  • [Presentation] An adaptive first order method for weakly smooth and uniformly convex problems2018

    • Author(s)
      Masaru Ito, Mituhiro Fukuda
    • Organizer
      The 23rd International Symposium on Mathematical Programming (ISMP2018)
    • Related Report
      2018 Research-status Report
    • Int'l Joint Research
  • [Presentation] p 次錐の自己同型群と非双対性2018

    • Author(s)
      伊藤勝, Bruno F. Lourenco
    • Organizer
      日本オペレーションズ・リサーチ学会 2018 年秋季研究発表会
    • Related Report
      2018 Research-status Report
  • [Presentation] 凸最適化に対する一次法の再出発法と未知パラメータへの適応2018

    • Author(s)
      伊藤勝・福田光浩
    • Organizer
      日本オペレーションズ・リサーチ学会 2018 年春季研究発表会
    • Related Report
      2017 Research-status Report

URL: 

Published: 2017-04-28   Modified: 2022-01-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi