On nonparametric randomized sketches for kernels with further smoothness

DOI10.1016/J.SPL.2019.06.001MaRDI QIDQ2322682zbMATH OpenOpenAlexFDO

Authors Xianzhu Xiong, Rui Li, Heng Lian

Publication date 5 September 2019

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.spl.2019.06.001

zbMATH Keywords

Rademacher complexityminimax ratekernel methodrandomized sketches

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07) Minimax procedures in statistical decision theory (62C20) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Recommendations

• Randomized sketches for kernels: fast and optimal nonparametric regression
• Faster kernel ridge regression using sketching and preconditioning
• Approximate nonparametric quantile regression in reproducing kernel Hilbert spaces via random projection
• Randomized sketches for kernel CCA
• Convergences of regularized algorithms and stochastic gradient methods with random projections

Cites work

• Consistent nonparametric regression. Discussion
• Distributed learning with regularized least squares
• Iterative Hessian sketch: fast and accurate solution approximation for constrained least-squares
• Minimax-optimal rates for sparse additive models over kernel classes via convex programming
• Optimal rates for the regularized least-squares algorithm
• Polynomial spline estimation for a generalized additive coefficient model
• Randomized Sketches of Convex Programs With Sharp Guarantees
• Randomized sketches for kernels: fast and optimal nonparametric regression
• Sketched ridge regression: optimization perspective, statistical perspective, and model averaging
• Sketching meets random projection in the dual: a provable recovery algorithm for big and high-dimensional data
• Some results on Tchebycheffian spline functions and stochastic processes
• Spline-backfitted kernel smoothing of nonlinear additive autoregression model

Cited in

(5)

• Randomized sketches for kernel CCA
• Randomized sketches for kernels: fast and optimal nonparametric regression
• Approximate nonparametric quantile regression in reproducing kernel Hilbert spaces via random projection
• Faster kernel ridge regression using sketching and preconditioning
• Nonasymptotic universal smoothing factors, kernel complexity and Yatracos classes

This page was built for publication: On nonparametric randomized sketches for kernels with further smoothness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2322682)