Some More Results on the Theory of Statistical Learning

http://ift.tt/1A9y6Rz

Yesterday, I did mention a popular graph discussed when studying theoretical foundations of statistical learning. But there is usually another one, which is the following, Let us get back to the underlying formulas. On the traning sample, we have some empirical risk, defined as for some loss function . Why is it complicated ? From the law of large numbers, when the ‘s are i.i.d., and . Here we look for It is difficult to say something about the limit, since the ‘s are … Continue reading Some More Results on the Theory of Statistical Learning →

from R-bloggers http://ift.tt/xdvlrq