The Annals of Statistics
- Ann. Statist.
- Volume 38, Number 1 (2010), 526-565.
Regularization in kernel learning
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.
Ann. Statist., Volume 38, Number 1 (2010), 526-565.
First available in Project Euclid: 31 December 2009
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Primary: 68Q32: Computational learning theory [See also 68T05]
Secondary: 60G99: None of the above, but in this section
Mendelson, Shahar; Neeman, Joseph. Regularization in kernel learning. Ann. Statist. 38 (2010), no. 1, 526--565. doi:10.1214/09-AOS728. https://projecteuclid.org/euclid.aos/1262271623