ML Anthology

Structural Risk Minimization for Nonparametric Time Series Prediction

Ron Meir
NeurIPS 1997 pp. 308-314
/neurips/1997/meir1997neurips-structural/

Abstract

The problem of time series prediction is studied within the uniform con(cid:173) vergence framework of Vapnik and Chervonenkis. The dependence in(cid:173) herent in the temporal structure is incorporated into the analysis, thereby generalizing the available theory for memoryless processes. Finite sam(cid:173) ple bounds are calculated in terms of covering numbers of the approxi(cid:173) mating class, and the tradeoff between approximation and estimation is discussed. A complexity regularization approach is outlined, based on Vapnik's method of Structural Risk Minimization, and shown to be ap(cid:173) plicable in the context of mixing stochastic processes.

PDF NeurIPS Semantic Scholar

Cite

Text

Meir. "Structural Risk Minimization for Nonparametric Time Series Prediction." Neural Information Processing Systems, 1997.

Markdown

[Meir. "Structural Risk Minimization for Nonparametric Time Series Prediction." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/meir1997neurips-structural/)

BibTeX

@inproceedings{meir1997neurips-structural,
  title     = {{Structural Risk Minimization for Nonparametric Time Series Prediction}},
  author    = {Meir, Ron},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {308-314},
  url       = {https://mlanthology.org/neurips/1997/meir1997neurips-structural/}
}