Learning theory and algorithms for forecasting non-stationary time series

Vitaly Kuznetsov, Mehryar Mohri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present data-dependent learning bounds for the general scenario of nonstationary 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.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages541-549
Number of pages9
Volume2015-January
StatePublished - 2015
Event29th Annual Conference on Neural Information Processing Systems, NIPS 2015 - Montreal, Canada
Duration: Dec 7 2015Dec 12 2015

Other

Other29th Annual Conference on Neural Information Processing Systems, NIPS 2015
CountryCanada
CityMontreal
Period12/7/1512/12/15

Fingerprint

Random processes
Time series

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Kuznetsov, V., & Mohri, M. (2015). Learning theory and algorithms for forecasting non-stationary time series. In Advances in Neural Information Processing Systems (Vol. 2015-January, pp. 541-549). Neural information processing systems foundation.

Learning theory and algorithms for forecasting non-stationary time series. / Kuznetsov, Vitaly; Mohri, Mehryar.

Advances in Neural Information Processing Systems. Vol. 2015-January Neural information processing systems foundation, 2015. p. 541-549.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kuznetsov, V & Mohri, M 2015, Learning theory and algorithms for forecasting non-stationary time series. in Advances in Neural Information Processing Systems. vol. 2015-January, Neural information processing systems foundation, pp. 541-549, 29th Annual Conference on Neural Information Processing Systems, NIPS 2015, Montreal, Canada, 12/7/15.
Kuznetsov V, Mohri M. Learning theory and algorithms for forecasting non-stationary time series. In Advances in Neural Information Processing Systems. Vol. 2015-January. Neural information processing systems foundation. 2015. p. 541-549
Kuznetsov, Vitaly ; Mohri, Mehryar. / Learning theory and algorithms for forecasting non-stationary time series. Advances in Neural Information Processing Systems. Vol. 2015-January Neural information processing systems foundation, 2015. pp. 541-549
@inproceedings{7b6ce3e19f514325bc1c51d32b3e451d,
title = "Learning theory and algorithms for forecasting non-stationary time series",
abstract = "We present data-dependent learning bounds for the general scenario of nonstationary 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.",
author = "Vitaly Kuznetsov and Mehryar Mohri",
year = "2015",
language = "English (US)",
volume = "2015-January",
pages = "541--549",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",

}

TY - GEN

T1 - Learning theory and algorithms for forecasting non-stationary time series

AU - Kuznetsov, Vitaly

AU - Mohri, Mehryar

PY - 2015

Y1 - 2015

N2 - We present data-dependent learning bounds for the general scenario of nonstationary 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.

AB - We present data-dependent learning bounds for the general scenario of nonstationary 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.

UR - http://www.scopus.com/inward/record.url?scp=84965144635&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84965144635&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2015-January

SP - 541

EP - 549

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -