English

Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering

Data Structures and Algorithms 2019-05-17 v1 Machine Learning

Abstract

We present tight lower bounds on the number of kernel evaluations required to approximately solve kernel ridge regression (KRR) and kernel kk-means clustering (KKMC) on nn input points. For KRR, our bound for relative error approximation to the minimizer of the objective function is Ω(ndeffλ/ε)\Omega(nd_{\mathrm{eff}}^\lambda/\varepsilon) where deffλd_{\mathrm{eff}}^\lambda is the effective statistical dimension, which is tight up to a log(deffλ/ε)\log(d_{\mathrm{eff}}^\lambda/\varepsilon) factor. For KKMC, our bound for finding a kk-clustering achieving a relative error approximation of the objective function is Ω(nk/ε)\Omega(nk/\varepsilon), which is tight up to a log(k/ε)\log(k/\varepsilon) factor. Our KRR result resolves a variant of an open question of El Alaoui and Mahoney, asking whether the effective statistical dimension is a lower bound on the sampling complexity or not. Furthermore, for the important practical case when the input is a mixture of Gaussians, we provide a KKMC algorithm which bypasses the above lower bound.

Keywords

Cite

@article{arxiv.1905.06394,
  title  = {Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel $k$-means Clustering},
  author = {Manuel Fernandez and David P. Woodruff and Taisuke Yasuda},
  journal= {arXiv preprint arXiv:1905.06394},
  year   = {2019}
}

Comments

27 pages, to appear in ICML 2019

R2 v1 2026-06-23T09:07:56.048Z