Learning Theory and Algorithms for Forecasting Non-stationary Time Series

Vitaly Kuznetsov; Mehryar Mohri

NeurIPS 2015oral114 citations

Learning Theory and Algorithms for Forecasting Non-stationary Time Series

Abstract

We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes. Our learning guarantees are expressed in terms of a data-dependent measure of sequential complexity and a discrepancy measure that can be estimated from data under some mild assumptions. We use our learning bounds to devise new algorithms for non-stationary time series forecasting for which we report some preliminary experimental results.

BibTeX

@inproceedings{NIPS2015_41f1f191,
 author = {Kuznetsov, Vitaly and Mohri, Mehryar},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {C. Cortes and N. Lawrence and D. Lee and M. Sugiyama and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Learning Theory and Algorithms for Forecasting Non-stationary Time Series},
 url = {https://proceedings.neurips.cc/paper_files/paper/2015/file/41f1f19176d383480afa65d325c06ed0-Paper.pdf},
 volume = {28},
 year = {2015}
}