The empirical error equation given in the book Understanding Machine Learning: From Theory to Algorithms is

enter image description here

My intuition for this equation is: total wrong predictions divided by the total number of samples $m$ in the given sample set $S$ (Correct me if I'm wrong). But, in this equation, the $m$ takes $\{ 1, \dots, m \}$. How is this actually calculated, as I thought it should be one number (the size of the sample)?


This is a commonly used notation in theoretical computer science.

$[m]$ is not the variable $m$, but is instead the set of integers from $1$ to $m$ inclusive. The empirical error equation thus reads in English:

The cardinality of a set consisting of the elements $i$ of the set of integers $[m]$ such that the hypothesis given input $x_i$ disagrees with label $y_i$, normalized by $m$.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.