Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity

Kamath Pritish
Kamath Pritish

COLT, pp. 2236-2262, 2020.

Cited by: 4|Views21
EI
Weibo:
We present and study approximate notions of dimensional and margin complexity, which correspond to the minimal dimension or norm of an embedding required to approximate, rather exactly represent, a given hypothesis class

Abstract:

We present and study approximate notions of dimensional and margin complexity, which correspond to the minimal dimension or norm of an embedding required to approximate, rather then exactly represent, a given hypothesis class. We show that such notions are not only sufficient for learning using linear predictors or a kernel, but unlike ...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments