On-line Prediction with Kernels and the Complexity Approximation Principle
Machine Learning
2012-07-19 v1 Machine Learning
Abstract
The paper describes an application of Aggregating Algorithm to the problem of regression. It generalizes earlier results concerned with plain linear regression to kernel techniques and presents an on-line algorithm which performs nearly as well as any oblivious kernel predictor. The paper contains the derivation of an estimate on the performance of this algorithm. The estimate is then used to derive an application of the Complexity Approximation Principle to kernel methods.
Cite
@article{arxiv.1207.4113,
title = {On-line Prediction with Kernels and the Complexity Approximation Principle},
author = {Alex Gammerman and Yuri Kalnishkan and Vladimir Vovk},
journal= {arXiv preprint arXiv:1207.4113},
year = {2012}
}
Comments
Appears in Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI2004)