Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data
Al-Naffouri, Tareq Y.
KAUST DepartmentElectrical Engineering Program
Physical Science and Engineering (PSE) Division
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Computer Science Program
KAUST Grant NumberOSR-CRG2019-4041
Preprint Posting Date2019-04-19
Online Publication Date2020-04-09
Print Publication Date2020-05
Permanent link to this recordhttp://hdl.handle.net/10754/660647
MetadataShow full item record
AbstractThis 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.
CitationElkhalil, K., Kammoun, A., Zhang, X., Alouini, M., & Al-Naffouri, T. (2020). Risk Convergence of Centered Kernel Ridge Regression with Large Dimensional Data. IEEE Transactions on Signal Processing, 1–1. doi:10.1109/tsp.2020.2975939
SponsorsThis work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award OSR-CRG2019-4041.