Sparsity and error analysis of empirical feature-based regularization schemes
From MaRDI portal
\(\ell^q\)-penaltyconcave regularizerregularization with empirical featuresreproducing kernel Hilbert spaceSCAD penaltysparsity
Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07) Learning and adaptive systems in artificial intelligence (68T05)
Recommendations
- An empirical feature-based learning algorithm producing sparse approximations
- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- An approximation theory approach to learning with \(\ell^1\) regularization
- Sparse kernel regression with coefficient-based \(\ell_q\)-regularization
- Optimal rate of the regularized regression learning algorithm
Cited in
(6)- Rates of convergence of randomized Kaczmarz algorithms in Hilbert spaces
- An empirical feature-based learning algorithm producing sparse approximations
- Learning theory of distributed regression with bias corrected regularization kernel network
- Thresholded spectral algorithms for sparse approximations
- Optimal learning with Gaussians and correntropy loss
- New Hilbert space tools for analysis of graph Laplacians and Markov processes
This page was built for publication: Sparsity and error analysis of empirical feature-based regularization schemes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3188011)
