Analysis of regularized Nyström subsampling for regression functions of low smoothness

DOI10.1142/S0219530519500039zbMath1440.68250arXiv1806.00826OpenAlexW2963705340MaRDI QIDQ5236751

Sergiy jun. Pereverzyev, Shuai Lu, Peter Mathé

Publication date: 10 October 2019

Published in: Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.00826

zbMATH Keywords

learning ratekernel learninglow smoothnessNyström subsampling

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)

Related Items

Semi-discrete Tikhonov regularization in RKHS with large randomly distributed noise, Regularized Nyström Subsampling in Covariate Shift Domain Adaptation Problems, Efficient kernel canonical correlation analysis using Nyström approximation, A multiscale RBF method for severely ill-posed problems on spheres, Sketching with Spherical Designs for Noisy Data Fitting on Spheres, Kernel conjugate gradient methods with random projections, The Goldenshluger-Lepski method for constrained least-squares estimators over RKHSs, Nyström subsampling method for coefficient-based regularized regression

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Regularization theory for ill-posed problems. Selected topics
• Unregularized online learning algorithms with general loss functions
• Learning sets with separating kernels
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Discrepancy based model selection in statistical inverse problems
• Learning theory estimates via integral operators and their approximations
• Convergence rates of Kernel Conjugate Gradient for random design regression
• Tikhonov regularization with oversmoothing penalty for non-linear ill-posed problems in Hilbert scales
• Error bounds for tikhonov regularization in hilbert scales
• A numerical differentiation method and its application to reconstruction of discontinuity
• Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions
• Thresholded spectral algorithms for sparse approximations
• Nyström type subsampling analyzed as a regularized projection
• How general are general source conditions?
• Detection of irregular points by regularization in numerical differentiation and application to edge detection
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality