ML Anthology

Competitive Online Generalized Linear Regression Under Square Loss

Fedor Zhdanov, Vladimir Vovk
ECML-PKDD 2010 pp. 531-546
doi:10.1007/978-3-642-15939-8_34 /ecmlpkdd/2010/zhdanov2010ecmlpkdd-competitive/

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.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Zhdanov and Vovk. "Competitive Online Generalized Linear Regression Under Square Loss." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2010. doi:10.1007/978-3-642-15939-8_34

Markdown

[Zhdanov and Vovk. "Competitive Online Generalized Linear Regression Under Square Loss." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2010.](https://mlanthology.org/ecmlpkdd/2010/zhdanov2010ecmlpkdd-competitive/) doi:10.1007/978-3-642-15939-8_34

BibTeX

@inproceedings{zhdanov2010ecmlpkdd-competitive,
  title     = {{Competitive Online Generalized Linear Regression Under Square Loss}},
  author    = {Zhdanov, Fedor and Vovk, Vladimir},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2010},
  pages     = {531-546},
  doi       = {10.1007/978-3-642-15939-8_34},
  url       = {https://mlanthology.org/ecmlpkdd/2010/zhdanov2010ecmlpkdd-competitive/}
}