Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

March 2010, Vol. 22, No. 3, Pages 793-829
(doi: 10.1162/neco.2009.05-08-786)
© 2009 Massachusetts Institute of Technology
Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data
Article PDF (290.08 KB)
Abstract

Various regularization techniques are investigated in supervised learning from data. Theoretical features of the associated optimization problems are studied, and sparse suboptimal solutions are searched for. Rates of approximate optimization are estimated for sequences of suboptimal solutions formed by linear combinations of n-tuples of computational units, and statistical learning bounds are derived. As hypothesis sets, reproducing kernel Hilbert spaces and their subsets are considered.