The fat shattering dimension generalizes the notion of VC-dimension to handle function classes where the range is $(0,1)$, instead of $\{0,1\}$. Fat shattering dimension plays the same role as VC-dimension in generalization bounds in machine learning.

While the concept (and related notions) is quite useful in machine learning, I've never seen it being used in "traditional" computational geometry, where VC-dimension (and the shatter dimension) play a significant role.

Are there any places where the fat shatter dimension has been used in computational geometry ?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.