Fixing an error in Caponnetto and de Vito (2007)

02/09/2017
by   Dougal J. Sutherland, et al.
0

The seminal paper of Caponnetto and de Vito (2007) provides minimax-optimal rates for kernel ridge regression in a very general setting. Its proof, however, contains an error in its bound on the effective dimensionality. In this note, we explain the mistake, provide a correct bound, and show that the main theorem remains true.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/12/2023

On the Optimality of Misspecified Kernel Ridge Regression

In the misspecified kernel ridge regression problem, researchers usually...
research
06/30/2020

Optimal Rates of Distributed Regression with Imperfect Kernels

Distributed machine learning systems have been receiving increasing atte...
research
03/23/2021

Comments on "A Framework for Control System Design Subject to Average Data-Rate Constraints"

Theorem  4.1 in the 2011 paper "A Framework for Control System Design Su...
research
03/16/2022

An elementary analysis of ridge regression with random design

In this note, we provide an elementary analysis of the prediction error ...
research
10/24/2016

Parallelizing Spectral Algorithms for Kernel Learning

We consider a distributed learning approach in supervised learning for a...
research
10/15/2017

The Complete Extensions do not form a Complete Semilattice

In his seminal paper that inaugurated abstract argumentation, Dung prove...
research
04/09/2021

How rotational invariance of common kernels prevents generalization in high dimensions

Kernel ridge regression is well-known to achieve minimax optimal rates i...

Please sign up or login with your details

Forgot password? Click here to reset