Pith. sign in

REVIEW 1 cited by

Fast Randomized Kernel Methods With Statistical Guarantees

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1411.0306 v3 pith:OK7LG4IF submitted 2014-11-02 stat.ML cs.LGstat.CO

Fast Randomized Kernel Methods With Statistical Guarantees

classification stat.ML cs.LGstat.CO
keywords kernelstatisticalmatrixtimeemphguaranteeslearningrunning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

One approach to improving the running time of kernel-based machine learning methods is to build a small sketch of the input and use it in lieu of the full kernel matrix in the machine learning task of interest. Here, we describe a version of this approach that comes with running time guarantees as well as improved guarantees on its statistical performance. By extending the notion of \emph{statistical leverage scores} to the setting of kernel ridge regression, our main statistical result is to identify an importance sampling distribution that reduces the size of the sketch (i.e., the required number of columns to be sampled) to the \emph{effective dimensionality} of the problem. This quantity is often much smaller than previous bounds that depend on the \emph{maximal degrees of freedom}. Our main algorithmic result is to present a fast algorithm to compute approximations to these scores. This algorithm runs in time that is linear in the number of samples---more precisely, the running time is $O(np^2)$, where the parameter $p$ depends only on the trace of the kernel matrix and the regularization parameter---and it can be applied to the matrix of feature vectors, without having to form the full kernel matrix. This is obtained via a variant of length-squared sampling that we adapt to the kernel setting in a way that is of independent interest. Lastly, we provide empirical results illustrating our theory, and we discuss how this new notion of the statistical leverage of a data point captures in a fine way the difficulty of the original statistical learning problem.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Beyond Averaging in John Ellipsoid Approximation: High-Accuracy Algorithms in the Leverage-Score Model

    math.OC 2026-06 unverdicted novelty 7.0

    John ellipsoid approximation in the leverage-score model achieves doubly logarithmic accuracy cost after setup by using last-iterate acceleration and Newton steps instead of averaging.