Analysis of regularized Nyström subsampling for regression functions of low smoothness
From MaRDI portal
Publication:5236751
DOI10.1142/S0219530519500039zbMATH Open1440.68250arXiv1806.00826OpenAlexW2963705340MaRDI QIDQ5236751FDOQ5236751
Sergiy jun. Pereverzyev, Shuai Lu, Peter Mathé
Publication date: 10 October 2019
Published in: Analysis and Applications (Search for Journal in Brave)
Abstract: This paper studies a Nystr"om type subsampling approach to large kernel learning methods in the misspecified case, where the target function is not assumed to belong to the reproducing kernel Hilbert space generated by the underlying kernel. This case is less understood, in spite of its practical importance. To model such a case, the smoothness of target functions is described in terms of general source conditions. It is surprising that almost for the whole range of the source conditions, describing the misspecified case, the corresponding learning rate bounds can be achieved with just one value of the regularization parameter. This observation allows a formulation of mild conditions under which the plain Nystr"om subsampling can be realized with subquadratic cost maintaining the guaranteed learning rates.
Full work available at URL: https://arxiv.org/abs/1806.00826
Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- An introduction to support vector machines and other kernel-based learning methods.
- Learning Bounds for Kernel Regression Using Effective Data Dimensionality
- Discrepancy based model selection in statistical inverse problems
- Regularization theory for ill-posed problems. Selected topics
- How general are general source conditions?
- Learning theory estimates via integral operators and their approximations
- A numerical differentiation method and its application to reconstruction of discontinuity
- Unregularized online learning algorithms with general loss functions
- Error bounds for tikhonov regularization in hilbert scales
- Convergence rates of kernel conjugate gradient for random design regression
- Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
- Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
- Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions
- Nyström type subsampling analyzed as a regularized projection
- Thresholded spectral algorithms for sparse approximations
- Learning sets with separating kernels
- Detection of irregular points by regularization in numerical differentiation and application to edge detection
Cited In (12)
- The Goldenshluger-Lepski method for constrained least-squares estimators over RKHSs
- Nyström subsampling method for coefficient-based regularized regression
- Efficient kernel canonical correlation analysis using Nyström approximation
- Iterative kernel regression with preconditioning
- Moduli of smoothness, \(K\)-functionals and Jackson-type inequalities associated with Kernel function approximation in learning theory
- A multiscale RBF method for severely ill-posed problems on spheres
- Semi-discrete Tikhonov regularization in RKHS with large randomly distributed noise
- Nyström landmark sampling and regularized Christoffel functions
- Sketching with Spherical Designs for Noisy Data Fitting on Spheres
- Adaptive parameter selection for kernel ridge regression
- Kernel conjugate gradient methods with random projections
- Regularized Nyström Subsampling in Covariate Shift Domain Adaptation Problems
Recommendations
- Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions 👍 👎
- Nyström subsampling method for coefficient-based regularized regression 👍 👎
- Nyström type subsampling analyzed as a regularized projection 👍 👎
- Subgradient and sampling algorithms for \(\ell_1\) regression 👍 👎
- Approximation of least squares regression on nested subspaces 👍 👎
- Manifold regularization based on Nyström type subsampling 👍 👎
- On Estimation Accuracy for Nonsmooth Functionals of Regression 👍 👎
- Title not available (Why is that?) 👍 👎
- Least-square regularized regression with non-iid sampling 👍 👎
This page was built for publication: Analysis of regularized Nyström subsampling for regression functions of low smoothness
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5236751)
