QUADRATIC AND CONVEX MINIMAX CLASSIFICATION PROBLEMS

スポンサーリンク

概要

• 論文の詳細を見る

• When there are two classes whose mean vectors and covariance matrices are known, Lanckriet et al. [7] consider the Linear Minimax Classification (LMC) problem and they propose a method for solving it. In this paper we first discuss the Quadratic Minimax Classification (QMC) problem, which is a generalization of LMC. We show that QMC is transformed to a parametric Semidefinite Programming (SDP) problem. We further define the Convex Minimax Classification (CMC) problem. Though the two problems are generalizations of LMC, we prove that solutions of these problems can be obtained by solving LMC.

著者

• Mizuno Shinji

  Tokyo Institute Of Technology

• Nakata Kazuhide

  Tokyo Institute Of Technology

• Kitahara Tomonari

  Tokyo Institute of Technology

• Kitahara Tomonari

  Tokyo Inst. Technol. Tokyo Jpn

• Mizuno Shinji

  Tokyo Inst. Technol. Tokyo Jpn

関連論文

• QUADRATIC AND CONVEX MINIMAX CLASSIFICATION PROBLEMS
• SDPA PROJECT : SOLVING LARGE-SCALE SEMIDEFINITE PROGRAMS(the 50th Anniversary of the Operations Research Society of Japan)
• 2-C-8 Performance Assessment of Philippine Administrative Divisions by Means of Data Envelopment Analysis
• AN EXTENSION OF A MINIMAX APPROACH TO MULTIPLE CLASSIFICATION
• LOWER BOUNDS FOR THE MAXIMUM NUMBER OF SOLUTIONS GENERATED BY THE SIMPLEX METHOD(SCOPE (Seminar on Computation and OPtimization for new Extensions))

スポンサーリンク