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

Determinantal point fields and machine learning

Research Project

Project/Area Number 20K20884
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 12:Analysis, applied mathematics, and related fields
Research InstitutionKyushu University

Principal Investigator

Shirai Tomoyuki  九州大学, マス・フォア・インダストリ研究所, 教授 (70302932)

Co-Investigator(Kenkyū-buntansha) 河原 吉伸  大阪大学, 大学院情報科学研究科, 教授 (00514796)
Project Period (FY) 2020-07-30 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2021: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2020: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Keywords行列式確率場 / 立方格子複体 / パーシステントホモロジー / 全域木・連結成分 / ラプラシアン / 機械学習 / 行列式点過程
Outline of Research at the Start

行列式確率場は複数の電子の反発的な振舞いを表現するために導入された確率モデルでしたが,現在では数学の様々な場面であらわれる重要なモデルであることがわかっています.一方機械学習はコンピュータを用いて大量のデータを学習することにより,分類や予測を行う効率的に工学的技術です.本研究は,これまでなかった機械学習の視点から行列式確率場を見直す数学的な研究を行うとともに,その機械学習への応用を目指すものです.

Outline of Final Research Achievements

To deepen understanding of determinantal probability in machine learning, the following research was conducted: enumeration of connected components when the number of cycles on a complete bipartite graph is fixed, determination of eigenvalues/eigenvectors of Laplacians on cubical complexes and their application in counting weighted spanning acycles and the system of partial differential equations satisfied by a family of exponential generating functions, comparison of representability of statistical models when modeling determinantal probability using L-matrices encompassing positive definite matrices and skew-symmetric matrices, approximation of Ginibre random point fields via perturbed lattices using distances based on persistence diagram and histograms of nearest-neighbors in point configurations. These studies have been published in international academic journals and are currently under submission.

Academic Significance and Societal Importance of the Research Achievements

行列式確率場は本来純粋数学的興味から研究が始まった研究対象であるが、機械学習への応用が提案されて以来,応用分野でも関心をもたれてきた.本研究は行列式確率場を具体的な問題に応用するという観点から実施し,特にハッシング,セルラーネットワーク,機械学習などの具体例に現れる行列式確率場に関わる数学的問題をとりあげた.これらの研究成果は,数学としての確率論および組合せ論の一分野に貢献するとともに,実世界の問題において応用される可能性も期待される.

Report

(5 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • Research Products

    (7 results)

All 2024 2022 2021 Other

All Int'l Joint Research (1 results) Journal Article (4 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 4 results,  Open Access: 4 results) Presentation (2 results) (of which Int'l Joint Research: 1 results,  Invited: 2 results)

  • [Int'l Joint Research] National University of Singapore(シンガポール)

    • Related Report
      2021 Research-status Report
  • [Journal Article] Torsion-weighted spanning acycle entropy in cubical lattices and Mahler measures2024

    • Author(s)
      Hiraoka Yasuaki、Shirai Tomoyuki
    • Journal Title

      Journal of Applied and Computational Topology

      Volume: 00 Issue: 6 Pages: 1-31

    • DOI

      10.1007/s41468-024-00163-y

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Local universality of determinantal point processes on Riemannian manifolds2022

    • Author(s)
      Makoto Katori and Tomoyuki Shirai
    • Journal Title

      Proceedings of Japan Academy

      Volume: 98 Pages: 95-100

    • Related Report
      2022 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Disordered complex networks: Energy optimal lattices and persistent homology2022

    • Author(s)
      Ghosh Subhroshekhar, Miyoshi Naoto, Shirai Tomoyuki
    • Journal Title

      IEEE Transactions on Information Theory

      Volume: Early Access Issue: 8 Pages: 1-1

    • DOI

      10.1109/tit.2022.3163604

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access / Int'l Joint Research
  • [Journal Article] Knowledge-Based Regularization in Generative Modeling2021

    • Author(s)
      河原吉伸
    • Journal Title

      Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

      Volume: IJCAI-20 Pages: 2390-2396

    • DOI

      10.24963/ijcai.2020/331

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] 行列式点過程の数理とその応用 ---ランダム行列から機械学習へ2022

    • Author(s)
      白井朋之
    • Organizer
      AIE講演会(東北大)
    • Related Report
      2022 Research-status Report
    • Invited
  • [Presentation] Persistent homology and its applications2022

    • Author(s)
      Tomoyuki Shirai
    • Organizer
      Blockchain Kaigi 2022 (BCK2022)
    • Related Report
      2022 Research-status Report
    • Int'l Joint Research / Invited

URL: 

Published: 2020-08-03   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi