Jethro's Braindump

Empirical Risk Minimization

In Machine Learning, the training set error is often called the empirical error or empirical risk, andn this is the error the classifier incurs over the sample:

\begin{equation} L_S(h) = \frac{|\{i \in [m] : h(x_i) \ne y_i\}}{m} \end{equation}

Given a hypothesis class \(H\), finding the hypothesis \(h \in H\) that minimizes the empirical risk is a simple learning strategy.

Icon by Laymik from The Noun Project. Website built with ♥ with Org-mode, Hugo, and Netlify.