An identity for kernel ridge regression

Authors:
Fedor Zhdanov;Yuri Kalnishkan
Affiliations:
Computer Learning Research Centre and Department of Computer Science, Royal Holloway, University of London, Surrey, United Kingdom;Computer Learning Research Centre and Department of Computer Science, Royal Holloway, University of London, Surrey, United Kingdom
Venue:
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
Year:
2010

Citing 9
Cited 1

Exponentiated gradient versus gradient descent for linear predictors

Information and Computation
Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions

Machine Learning
Ridge Regression Learning Algorithm in Dual Variables

ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Tracking the best linear predictor

The Journal of Machine Learning Research
Prediction, Learning, and Games

Prediction, Learning, and Games
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)

Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
Online Regression Competitive with Changing Predictors

ALT '07 Proceedings of the 18th international conference on Algorithmic Learning Theory
Information Consistency of Nonparametric Gaussian Process Methods

IEEE Transactions on Information Theory
Worst-case quadratic loss bounds for prediction using linear functions and gradient descent

IEEE Transactions on Neural Networks

2013 Special Issue: Real-time model learning using Incremental Sparse Spectrum Gaussian Process Regression

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper provides a probabilistic derivation of an identity connecting the square loss of ridge regression in on-line mode with the loss of a retrospectively best regressor. Some corollaries of the identity providing upper bounds for the cumulative loss of on-line ridge regression are also discussed.