Tomomi Matsui

Mixed Integer Quadratic Optimization Formulations for Eliminating Multicollinearity Based on Variance Inflation Factor

  • Ken Kobayashi
  • Tomomi Matsui
  • Ryuhei Miyashiro
  • Kazuhide Nakata
  • Yuichi Takano
  • Ryuta Tamura
    • Categories Applications - Science and Engineering, Integer Programming, Statistics Tags , , , , ,

    The variance inflation factor, VIF, is the most frequently used indicator for detecting multicollinearity in multiple linear regression models. This paper proposes two mixed integer quadratic optimization formulations for selecting the best subset of explanatory variables under upper-bound constraints on VIF of selected variables. Computational results illustrate the effectiveness of our optimization formulations based on … Read more

    Best subset selection for eliminating multicollinearity

  • Ken Kobayashi
  • Tomomi Matsui
  • Ryuhei Miyashiro
  • Kazuhide Nakata
  • Yuichi Takano
  • Ryuta Tamura
    • Categories Applications - Science and Engineering, Global Optimization, Integer Programming Tags , , , , ,

    This paper proposes a method for eliminating multicollinearity from linear regression models. Specifically, we select the best subset of explanatory variables subject to the upper bound on the condition number of the correlation matrix of selected variables. We first develop a cutting plane algorithm that, to approximate the condition number constraint, iteratively appends valid inequalities … Read more

    A doubly nonnegative relaxation for modularity density maximization

  • Yoichi Izunaga
  • Tomomi Matsui
  • Yoshitsugu Yamamoto
    • Categories Combinatorial Optimization, Linear, Cone and Semidefinite Programming Tags , , ,

    Modularity proposed by Newman and Girvan is the most commonly used measure when the nodes of a graph are grouped into communities consisting of tightly connected nodes. However, some authors pointed out drawbacks of the modularity, the main issue of which is resolution limit. Resolution limit refers to the sensitivity of the modularity to the … Read more

    On the Number of Solutions Generated by Dantzig’s Simplex Method for LP with Bounded Variables

  • Tomonari Kitahara
  • Tomomi Matsui
  • Shinji Mizuno
    • Categories Linear Programming Tags , , , , ,

    We give an upper bound for the number of different basic feasible solutions generated by Dantzig’s simplex method (the simplex method with the most negative pivoting rule) for LP with bounded variables by extending the result of Kitahara and Mizuno (2010). We refine the analysis by them and improve an upper bound for a standard … Read more

    Semidefinite Programming Based Approaches to Home-away Assignment Problems in Sports Scheduling

  • Tomomi Matsui
  • Ryuhei Miyashiro
  • Akiko Yoshise
  • Ayami Suzuka
    • Categories Approximation Algorithms

    For a given schedule of a round-robin tournament and a matrix of distances between homes of teams, an optimal home-away assignment problem is to find a home-away assignment that minimizes the total traveling distance. We propose a technique to transform the problem to MIN RES CUT. We apply Goemans and Williamson’s 0.878-approximation algorithm for MAX … Read more