User Tools

Site Tools


Data Science Seminar
Hosted by Department of Mathematical Sciences

  • Date: Tuesday, April 24, 2018
  • Time: 12:05pm – 1:05pm
  • Room: WH-100E
  • Speaker: Haomiao Meng (Binghamton University)
  • Title: Multicategory Angle-based Large-margin Classification


Large-margin classifiers are popular methods for classification. Among existing simultaneous multicategory large-margin classifiers, a common approach is to learn k different functions for a k-class problem with a sum-to-zero constraint. Such a formulation can be inefficient. We propose a new multicategory angle-based large-margin classification framework. The proposed angle-based classifiers consider a simplex-based prediction rule without the sum-to-zero constraint, and enjoy more efficient computation. Many binary large-margin classifiers can be naturally generalized for multicategory problems through the angle-based framework. Theoretical and numerical studies demonstrate the usefulness of the angle-based methods.

seminars/datasci/180410.txt · Last modified: 2018/04/22 20:31 by gang