Definition
The goal of learning is usually to find a model which delivers good generalization performance over an underlying distribution of the data. Consider an input space \(\mathcal{X}\) and output space \(\mathcal{Y}\). Assume the pairs \((X \times Y ) \in \mathcal{X}\times \mathcal{Y}\) are random variables whose (unknown) joint distribution is P XY . It is our goal to find a predictor \(f : \mathcal{X}\mapsto \mathcal{Y}\) which minimizes the expected risk:
where δ(z) = 1 if z is true, and 0 otherwise.
However, in practice we only have n pairs of training examples (X i , Y i ) drawn identically and independently from P XY . Since P XY is unknown, we often use the risk on the training set (called empirical risk) as a surrogate of the expected risk on the underlying distribution:
Empirical Risk...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Recommended Reading
Vapnik V (1998) Statistical learning theory. John Wiley and Sons, New York
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Science+Business Media New York
About this entry
Cite this entry
Zhang, X. (2017). Empirical Risk Minimization. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning and Data Mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1_79
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7687-1_79
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7685-7
Online ISBN: 978-1-4899-7687-1
eBook Packages: Computer ScienceReference Module Computer Science and Engineering