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

We present tight lower bounds on the number of kernel evaluations required to approximately solve kernel ridge regression (KRR) and kernel -means clustering (KKMC) on input points. For KRR, our bound for relative error approximation to the minimizer of the objective function is where is the effective statistical dimension, which is tight up to a factor. For KKMC, our bound for finding a -clustering achieving a relative error approximation of the objective function is , which is tight up to a 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.
View on arXiv