Indefinite kernel network with l^q-norm regularization
From MaRDI portal
Indefinite kernel network with \(l^q\)-norm regularization
Summary: We study the asymptotical properties of indefinite kernel network with \(l^q\)-norm regularization. The framework under investigation is different from classical kernel learning. Positive semidefiniteness is not required by the kernel function. By a new step stone technique, without any interior cone condition for input space \(\mathcal{X}\) and \(L_\tau\) condition for the probability measure \(\rho_{\mathcal{X}}\), satisfied error bounds and learning rates are deduced.
Recommendations
Cites work
- 10.1162/153244302760200704
- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- Indefinite kernel network with dependent sampling
- Learning by nonsymmetric kernels with data dependent spaces and \(\ell^1\)-regularizer
- Learning rates of least-square regularized regression
- Learning rates of regularized regression for exponentially strongly mixing sequence
- Learning Theory
- Learning theory estimates for coefficient-based regularized regression
- Learning theory estimates via integral operators and their approximations
- Learning with sample dependent hypothesis spaces
- Least square regression with indefinite kernels and coefficient regularization
- Leave-One-Out Bounds for Kernel Methods
- Regularized least square regression with dependent samples
- Theory of Reproducing Kernels
This page was built for publication: Indefinite kernel network with \(l^q\)-norm regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1723692)
