On the additive properties of the fat-shattering dimension

IEEE Trans Neural Netw Learn Syst. 2014 Dec;25(12):2309-12. doi: 10.1109/TNNLS.2014.2327065.

Abstract

The properties of the VC-dimension under various compositions are well-understood, but this is much less the case for classes of continuous functions. In this brief, we show that a commonly used scale-sensitive dimension, Vγ, is much less well-behaved under Minkowski summation than its VC cousin, while the fat-shattering dimension retains some compositional similarity to the VC-dimension. As an application, we analyze the fat-shattering dimension of trigonometric functions and series.

Publication types

  • Research Support, Non-U.S. Gov't