Discrepancy-Based Theory and Algorithms for Forecasting Non-Stationary Time Series

被引：20

作者：

Kuznetsov, Vitaly ^{[1
]}

Mohri, Mehryar ^{[2
]}

机构：

[1] Google Res, 76 Ninth Ave, New York, NY 10011 USA

[2] Google Res & Courant Inst, 251 Mercer St, New York, NY 10012 USA

来源：

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE | 2020年 / 88卷 / 04期

关键词：

Time series; Forecasting; Non-stationary; Non-mixing; Generalization bounds; Discrepancy; Expected sequential covering numbers; Sequential Rademacher complexity; CONVERGENCE; PREDICTION; BOUNDS;

D O I：

10.1007/s10472-019-09683-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. Our learning bounds guide the design of new algorithms for non-stationary time series forecasting for which we report several favorable experimental results.

引用

页码：367 / 399

页数：33

共 50 条

[31] Methods for generating non-stationary current, wind and wave time series in the time domain
Mo, K
Reinholdtsen, SA
PROCEEDINGS OF THE THIRTEENTH (2003) INTERNATIONAL OFFSHORE AND POLAR ENGINEERING CONFERENCE, VOL 3, 2003, : 277 - 285
[32] On the interaction between forecasting and stock control: The case of non-stationary demand
Strijbosch, Leo W. G.
Syntetos, Aris A.
Boylan, John E.
Janssen, Elleke
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2011, 133 (01) : 470 - 480
[33] Weakly convergent nonparametric forecasting of stationary time series
Morvai, G
Yakowitz, SJ
Algoet, P
IEEE TRANSACTIONS ON INFORMATION THEORY, 1997, 43 (02) : 483 - 498
[34] An improved deep echo state network inspired by tissue-like P system forecasting for non-stationary time series
Yang, Xiaojian
Liu, Qian
Liu, Xiyu
Xue, Jie
JOURNAL OF MEMBRANE COMPUTING, 2022, 4 (03) : 222 - 231
[35] Causal structure learning for high-dimensional non-stationary time series
Chen, Siya
Wu, HaoTian
Jin, Guang
KNOWLEDGE-BASED SYSTEMS, 2024, 295
[36] Auto-Regressive Models of Non-Stationary Time Series with Finite Length
费万春
白伦
TsinghuaScienceandTechnology, 2005, (02) : 162 - 168
[37] Order selection for possibly infinite-order non-stationary time series
Sin, Chor-Yiu
Yu, Shu-Hui
ASTA-ADVANCES IN STATISTICAL ANALYSIS, 2019, 103 (02) : 187 - 216
[38] A new threshold selection method for peak over for non-stationary time series
Zhou, C. R.
Chen, Y. F.
Gu, S. H.
Huang, Q.
Yuan, J. C.
Yu, S. N.
INTERNATIONAL CONFERENCE ON WATER RESOURCE AND ENVIRONMENT 2016 (WRE2016), 2016, 39
[39] Order selection for possibly infinite-order non-stationary time series
Chor-yiu Sin
Shu-Hui Yu
AStA Advances in Statistical Analysis, 2019, 103 : 187 - 216
[40] Estimating the parameters of a BINMA Poisson model for a non-stationary bivariate time series
Sunecher, Yuvraj
Khan, Naushad Mamode
Jowaheer, Vandna
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2017, 46 (09) : 6803 - 6827

← 1 2 3 4 5 →