Learning theory and algorithms for forecasting non-stationary time series

Vitaly Kuznetsov; Mehryar Mohri

Learning theory and algorithms for forecasting non-stationary time series

Computer Science

Research output: Contribution to journal › Conference article › peer-review

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 language	English (US)
Pages (from-to)	541-549
Number of pages	9
Journal	Advances in Neural Information Processing Systems
Volume	2015-January
State	Published - 2015
Event	29th Annual Conference on Neural Information Processing Systems, NIPS 2015 - Montreal, Canada Duration: Dec 7 2015 → Dec 12 2015

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{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",

note = "Funding Information: This work was partly funded by NSF IIS-1117591 and CCF-1535987, and the NSERC PGS D3.; 29th Annual Conference on Neural Information Processing Systems, NIPS 2015 ; Conference date: 07-12-2015 Through 12-12-2015",

year = "2015",

language = "English (US)",

volume = "2015-January",

pages = "541--549",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

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

AU - Kuznetsov, Vitaly

AU - Mohri, Mehryar

N1 - Funding Information: This work was partly funded by NSF IIS-1117591 and CCF-1535987, and the NSERC PGS D3.

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 article

AN - SCOPUS:84965144635

SN - 1049-5258

VL - 2015-January

SP - 541

EP - 549

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 29th Annual Conference on Neural Information Processing Systems, NIPS 2015

Y2 - 7 December 2015 through 12 December 2015

ER -

Learning theory and algorithms for forecasting non-stationary time series

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this