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:
“It is a general popular error to suppose the loudest complainers for the public to be the most anxious for its welfare.”
—Edmund Burke (1729–1797)
“Great Wits are sure to Madness near alli’d
And thin Partitions do their Bounds divide;
Else, why should he, with Wealth and Honour blest,
Refuse his Age the needful hours of Rest?”
—John Dryden (1631–1700)