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 an old error of man to forget to put quotation marks where he borrows from a woman’s brain!”
—Anna Garlin Spencer (1851–1931)
“What comes over a man, is it soul or mind
That to no limits and bounds he can stay confined?
You would say his ambition was to extend the reach
Clear to the Arctic of every living kind.
Why is his nature forever so hard to teach
That though there is no fixed line between wrong and right,
There are roughly zones whose laws must be obeyed?”
—Robert Frost (1874–1963)