this is for holding javascript data
Konstantinos Makantasis edited untitled.tex
over 8 years ago
Commit id: 9a9274638876af227b1ad59162461334646a3739
deletions | additions
diff --git a/untitled.tex b/untitled.tex
index 18ce624..769bdd3 100644
--- a/untitled.tex
+++ b/untitled.tex
...
\end{equation}
The first part of the theorem is proven.
For proving the second part of the theorem, we have to show that whenever uniform one-sided convergence of mean to their mathematical expectations takes place, the ERM principle is strictly consistent, that is,
taht that for any $\epsilon$ the convergence
\begin{equation}
P\bigg \{ \bigg | \inf_{a \in \Lambda(c)} \int Q(z,a)dF(z) - \inf_{a \in \Lambda(c)} \frac{1}{l} \sum_{i=1}^{l}Q(z_i,a)\bigg | > \epsilon \bigg \} \xrightarrow[l \rightarrow \infty]{} 0
\end{equation}