An approximation theory approach to learning with \(\ell^1\) regularization (Q1944318)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | An approximation theory approach to learning with \(\ell^1\) regularization |
scientific article |
Statements
An approximation theory approach to learning with \(\ell^1\) regularization (English)
0 references
5 April 2013
0 references
Kernel based regularization schemes with an \(l^1\)-regularizer and a general loss function are studied. Assuming that the input data space \(X\) satisfies an interior cone condition and some regularity conditions on the marginal distribution and target functions as well as an appropriate smoothness condition on the kernel, an error analysis is carried out by means of a local polynomial reproduction formula of approximation theory. An error bound is proved and learning rates are improved which are independent of the dimension of \(X\).
0 references
learning theory
0 references
data dependent hypothesis spaces
0 references
kernel-based regularization scheme
0 references
\(\ell ^{1}\)-regularizer
0 references
multivariate approximation
0 references
data dependent hypothesis space
0 references
\(l^1\)-regularizer multivariate approximation
0 references