Competitive online generalized linear regression under square loss

Authors:
Fedor Zhdanov;Vladimir Vovk
Affiliations:
Computer Learning Research Centre and Department of Computer Science, Royal Holloway, University of London, Egham, Surrey, England;Computer Learning Research Centre and Department of Computer Science, Royal Holloway, University of London, Egham, Surrey, England
Venue:
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part III
Year:
2010

Citing 7
Cited 0

Tracking the Best Expert

Machine Learning - Special issue on context sensitivity and concept drift
Derandomizing Stochastic Prediction Strategies

Machine Learning - Special issue: computational learning theory, COLT '97
Relative Loss Bounds for Multidimensional Regression Problems

Machine Learning
On Relative Loss Bounds in Generalized Linear Regression

FCT '99 Proceedings of the 12th International Symposium on Fundamentals of Computation Theory
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Logarithmic regret algorithms for online convex optimization

Machine Learning
Forecasting skewed biased stochastic ozone days: analyses, solutions and beyond

Knowledge and Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We apply the Aggregating Algorithm to the problem of online regression under the square loss function. We develop an algorithm competitive with the benchmark class of generalized linear models (our "experts"), which are used in a wide range of practical tasks. This problem does not appear to be analytically tractable. Therefore, we develop a prediction algorithm using the Markov chain Monte Carlo method, which is shown to be fast and reliable in many cases. We prove upper bounds on the cumulative square loss of the algorithm. We also perform experiments with our algorithm on a toy data set and two real world ozone level data sets and give suggestions about choosing its parameters.