ISLR_ch9.1 Maximal_Margin_Classifier

ISLR_ch9.1 Maximal_Margin_Classifier

What Is a Hyperplane?

In a p-dimensional space, a hyperplane is a flat affine subspace of hyperplanedimension p − 1. For instance, in two dimensions, a hyperplane is a flat one-dimensional subspace—in other words, a line. In three dimensions, a hyperplane is a flat two-dimensional subspace—that is, a plane. In p > 3 dimensions, it can be hard to visualize a hyperplane, but the notion of a (p − 1)-dimensional flat subspace still applies. The mathematical definition of a hyperplane is quite simple. In two dimensions, a hyperplane is defined by the equation

The word affine indicates that the subspace need not pass through the origin.

A p dimensional hyperplane is defined as

$$ \normalsize \beta_{0} + \beta_{1}X_{1} + \beta_{2}X_{2} +\ …\ + \beta_{p}X_{p} = 0 $$

which means that any $$ X = (X_{1},\ X_{2},\ …,\ X_{p})^{T} $$ for which the above hyperplane equation holds is a point on the hyperplane.

If $ X = (X_{1},\ X_{2},\ …,\ X_{p})^{T} $ doesn’t fall on the hyperplane, then it must fall on one side of the hyperplane or the other. As such, a hyperplane can be thought of as dividing a $ p $-dimensional space into two partitions. Which side of the hyperplane a point falls on can be computed by calculating the sign of the result of plugging the point into the hyperplane equation.

Classification Using a Separating Hyperplane

The Maximal Margin Classifier

advantage: it is elegant and simple, disadvantage: it cannot be applied to most data sets, since it requires that the classes be separable by a linear boundary.

Construction of the Maximal Margin Classifier

The Non-separable Case


  TOC