Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

This paper carries out a large dimensional analysis of a variation of kernel ridge regression that we call centered kernel ridge regression (CKRR), also known in the literature as kernel ridge regression with offset. This modified technique is obtained by accounting for the bias in the regression problem resulting in the old kernel ridge regression but with centered kernels. The analysis is carried out under the assumption that the data is drawn from a Gaussian distribution and heavily relies on tools from random matrix theory (RMT). Under the regime in which the data dimension and the training size grow infinitely large with fixed ratio and under some mild assumptions controlling the data statistics, we show that both the empirical and the prediction risks converge to a deterministic quantities that describe in closed form fashion the performance of CKRR in terms of the data statistics and dimensions. Inspired by this theoretical result, we subsequently build a consistent estimator of the prediction risk based on the training data which allows to optimally tune the design parameters. A key insight of the proposed analysis is the fact that asymptotically a large class of kernels achieve the same minimum prediction risk. This insight is validated with both synthetic and real data.
Original languageEnglish (US)
Pages (from-to)1574-1588
Number of pages15
JournalIEEE Transactions on Signal Processing
Volume68
DOIs
StatePublished - 2020

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data'. Together they form a unique fingerprint.

Cite this