The Vapnik-Chervonenkis (VC) dimension is a theoretical measure of the complexity or 'capacity' of a statistical classification algorithm. It is defined as the size of the largest set of points that the algorithm can 'shatter' (classify correctly for all possible label assignments).
Introduced by Vladimir Vapnik and Alexey Chervonenkis in 1968.
A foundational concept in Computational Learning Theory that mathematically explains why simpler models generalize better.