Convergence of Large Margin Separable Linear Classification

Free registration required

Executive Summary

Large margin linear classification methods have been successfully applied to many applications. For a linearly separable problem, it is known that under appropriate assumptions, the expected misclassification error of the computed "Optimal hyperplane" approaches zero at a rate proportional to the inverse training sample size. This rate is usually characterized by the margin and the maximum norm of the input data. In this paper, the paper argues that another quantity, namely the robustness of the input data distribution, also plays an important role in characterizing the convergence behavior of expected misclassification error. Based on this concept of robustness, one shows that for a large margin separable linear classification problem, the expected misclassification error may converge exponentially in the number of training sample size.

  • Format: PDF
  • Size: 82.4 KB