Misclassification risk ( $R (h)$ )

The misclassification risk of a classifier is its expected misclassification loss,

R (h) = P (h (X) \neq = Y) = E ℓ_{0 - 1} (h, (X, Y)) .

Table of contents
- Empirical misclassification risk Misclassification risk

Empirical misclassification risk ( $R (h)$ )

On labelled examples

Z_{1}, \dots, Z_{n}

, the empirical misclassification risk is

R (h) = \frac{1}{n} \sum_{i = 1}^{n} ℓ_{0 - 1} (h, Z_{i}) .

An empirical risk minimizer chooses a classifier attaining the smallest value over its hypothesis class.

 Ancestors (8)

 Incoming links (2)

Past exam of the mathematics course of the University of Cambridge / 2020 / ii / Paper 1 / 31J / b / Solution
Rademacher excess-risk bound for empirical risk minimization

 View article source

 Discussion (0)

There are no discussions about this article yet.

 Articles by others on the same topic (0)

There are currently no matching articles.

  See all articles in the same topic Create my own version