Generalization Error Bounds
One theoretical motivation behind margin classifiers is that their generalization error may be bound by parameters of the algorithm and a margin term. An example of such a bound is for the AdaBoost algorithm. Let be a set of examples sampled independently at random from a distribution . Assume the VC-dimension of the underlying base classifier is and . Then with probability we have the bound
for all .
Read more about this topic: Margin Classifier
Famous quotes containing the words error and/or bounds:
“I have often been reproached with the aridity of my genius; a deficiency of imagination has been imputed to me as a crime; and the Pyrrhonism of my opinions has at all times rendered me notorious. Indeed, a strong relish for physical philosophy has, I fear, tinctured my mind with a very common error of this age—I mean the habit of referring occurrences, even the least susceptible of such reference, to the principles of that science.”
—Edgar Allan Poe (1809–1849)
“At bounds of boundless void.”
—Samuel Beckett (1906–1989)