Out-of-sample error equals in-sample error plus a penalty for model complexity
Y.S. Abu-Mostafa, in explaining the VC inequality of PAC learning.
This quote leaves out the ‘P’ part of “PAC”! It should really read,
Out-of-sample error equals in-sample error plus a penalty for model complexity… probably.
Y.S. Abu-Mostafa, in explaining the VC inequality of PAC learning.
This quote leaves out the ‘P’ part of “PAC”! It should really read,