Randomized sketches for kernels: fast and optimal nonparametric regression

DOI10.1214/16-AOS1472zbMath1371.62039arXiv1501.06195OpenAlexW2962937842MaRDI QIDQ2012925

Yun Yang, Mert Pilanci, Martin J. Wainwright

Publication date: 3 August 2017

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1501.06195

zbMATH Keywords

convex optimizationkernel methodnonparametric regressiondimensionality reductionrandom projectionkernel ridge regression (KRR)

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Randomized algorithms (68W20)

Related Items (28)

Efficient kernel-based variable selection with sparsistency ⋮ Vecchia-Laplace approximations of generalized Gaussian processes for big non-Gaussian spatial data ⋮ Disentangled Representation Learning and Generation With Manifold Optimization ⋮ Functional principal subspace sampling for large scale functional data analysis ⋮ Smoothing Splines Approximation Using Hilbert Curve Basis Selection ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Concentration of kernel matrices with application to kernel spectral clustering ⋮ Faster Kernel Ridge Regression Using Sketching and Preconditioning ⋮ Distributed learning for sketched kernel regression ⋮ Distributed Bayesian inference in massive spatial data ⋮ Decentralized learning over a network with Nyström approximation using SGD ⋮ Optimal subsampling algorithms for composite quantile regression in massive data ⋮ On the coercivity condition in the learning of interacting particle systems ⋮ Optimally tackling covariate shift in RKHS-based nonparametric regression ⋮ From Gauss to Kolmogorov: localized measures of complexity for ellipses ⋮ Nonparametric distributed learning under general designs ⋮ Spectrally-truncated kernel ridge regression and its free lunch ⋮ Kernel conjugate gradient methods with random projections ⋮ Randomized sketches for kernel CCA ⋮ On b-bit min-wise hashing for large-scale regression and classification with sparse data ⋮ Approximate nonparametric quantile regression in reproducing kernel Hilbert spaces via random projection ⋮ Consistent online Gaussian process regression without the sample complexity bottleneck ⋮ On nonparametric randomized sketches for kernels with further smoothness ⋮ Unnamed Item ⋮ Approximate kernel PCA: computational versus statistical trade-off

This page was built for publication: Randomized sketches for kernels: fast and optimal nonparametric regression