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
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
收藏
页码:367 / 399
页数:33
相关论文
共 50 条
  • [1] Discrepancy-Based Theory and Algorithms for Forecasting Non-Stationary Time Series
    Vitaly Kuznetsov
    Mehryar Mohri
    Annals of Mathematics and Artificial Intelligence, 2020, 88 : 367 - 399
  • [2] Learning Theory and Algorithms for Forecasting Non-Stationary Time Series
    Kuznetsov, Vitaly
    Mohri, Mehryar
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), 2015, 28
  • [3] Forecasting smoothed non-stationary time series using genetic algorithms
    Norouzzadeh, P.
    Rahmani, B.
    Norouzzadeh, M. S.
    INTERNATIONAL JOURNAL OF MODERN PHYSICS C, 2007, 18 (06): : 1071 - 1086
  • [4] Forecasting in non-stationary environments with fuzzy time series
    de Lima e Silva, Petronio Candido
    Severiano Junior, Carlos Alberto
    Alves, Marcos Antonio
    Silva, Rodrigo
    Cohen, Miri Weiss
    Guimaraes, Frederico Gadelha
    APPLIED SOFT COMPUTING, 2020, 97
  • [5] Forecasting non-stationary economic time series.
    Rothman, P
    JOURNAL OF ECONOMIC LITERATURE, 2001, 39 (02) : 570 - 572
  • [6] Forecasting non-stationary economic time series.
    Öller, LE
    INTERNATIONAL JOURNAL OF FORECASTING, 2001, 17 (01) : 133 - 134
  • [7] Non-stationary financial time series forecasting based on meta-learning
    Hong, Anqi
    Gao, Minghan
    Gao, Qiang
    Peng, Xiao-Hong
    ELECTRONICS LETTERS, 2023, 59 (01)
  • [8] Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
    Liu, Yong
    Wu, Haixu
    Wang, Jianmin
    Long, Mingsheng
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [9] Forecasting non-stationary time series by wavelet process modelling
    Piotr Fryzlewicz
    Sébastien Van Bellegem
    Rainer von Sachs
    Annals of the Institute of Statistical Mathematics, 2003, 55 : 737 - 764
  • [10] Forecasting non-stationary time series by wavelet process modelling
    Fryzlewicz, P
    Van Bellegem, S
    von Sachs, R
    ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 2003, 55 (04) : 737 - 764