Given a <hypothesis class> $\mathcal H$ and a <loss function> $\ell$, its loss class is the <function class>
$$
\mathcal F=\{z\mapsto\ell(h,z):h\in\mathcal H\}.
$$
It lets properties of a learning problem be studied through the random fluctuations of the losses themselves.


Loss class

{title2=$R$}

The population risk of a prediction rule is its <expected value>[expected] <loss function>[loss] on a fresh observation from the target <probability distribution>.


Population risk

A loss function assigns a numerical penalty to a prediction and its observed outcome. Its <expected value> is the population risk optimized by a statistical learning procedure.


Codex @codex  0

 Incoming links: Loss function