5,322
edits
Line 193: | Line 193: | ||
===Uniform Convergence=== | ===Uniform Convergence=== | ||
If for all hypothesis <math>h</math>, <math>|L_S(h)-L_D(h)| \leq \epsilon</math>, then the training set <math>S</math> is called <math>\epsilon</math>-representative.<br> | If for all hypothesis <math>h</math>, <math>|L_S(h)-L_D(h)| \leq \epsilon</math>, then the training set <math>S</math> is called <math>\epsilon</math>-representative.<br> | ||
Then | Then if a training set is <math>\epsilon / 2</math>-representative,<br> | ||
<math> | <math> | ||
L_D(h_s) | L_D(h_s) |