Structural risk minimization

Structural Risk Minimization (SRM) is an inductive principle of use in machine learning. Commonly in machine learning, a generalized model must be selected from a finite data set, with the consequent problem of overfitting - the model becoming too strongly tailored to the particularities of the training set and generalizing poorly to new data. The SRM principle tries to counter this problem by balancing the model's complexity against its success at fitting the training data.

SRM was first set out in a 1974 by Vladimir Vapnik and Alexey Chervonenkis.

See also

• Vapnik-Chervonenkis theory
• Support Vector Machines

External links

• http://www.svms.org/srm/