Regularization in kernel learning
Mendelson, Shahar ; Neeman, Joseph
Ann. Statist., Tome 38 (2010) no. 1, p. 526-565 / Harvested from Project Euclid
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.
Publié le : 2010-02-15
Classification:  Regression,  reproducing kernel Hilbert space,  regulation,  least-squares,  model selection,  68Q32,  60G99
@article{1262271623,
     author = {Mendelson, Shahar and Neeman, Joseph},
     title = {Regularization in kernel learning},
     journal = {Ann. Statist.},
     volume = {38},
     number = {1},
     year = {2010},
     pages = { 526-565},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1262271623}
}
Mendelson, Shahar; Neeman, Joseph. Regularization in kernel learning. Ann. Statist., Tome 38 (2010) no. 1, pp.  526-565. http://gdmltest.u-ga.fr/item/1262271623/