Masaq Index
arXiv 2010-01-13 DOI 10.1214/09-AOS728 0 views

Regularization in kernel learning

Mendelson, Shahar · Neeman, Joseph

Original · EN

Under mild assumptions on the kernel, we obtain the best known error rates in a regularized learning scenario taking place in the corresponding reproducing kernel Hilbert space (RKHS). The main novelty in the analysis is a proof that one can use a regularization term that grows significantly slower than the standard quadratic growth in the RKHS norm.

English translation

This paper has no Arabic translation yet. Be the first: it takes a few seconds, and the result is stored for every future reader.

Security check

Type the characters above

Up to 10 translations per person per day.