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

被引:24
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 45 条
[21]  
Gine E., 1999, Decoupling: from dependence to independence
[22]  
Hamilton J. D., 1994, Time series analysis
[23]  
Kuznetsov V., 2015, NIPS
[24]  
Kuznetsov V., 2016, COLT
[25]  
Kuznetsov V., 2019, AISTATS
[26]   Generalization bounds for non-stationary mixing processes [J].
Kuznetsov, Vitaly ;
Mohri, Mehryar .
MACHINE LEARNING, 2017, 106 (01) :93-117
[27]  
Kuznetsov Vitaly, 2014, LECT NOTES COMPUTER, P260
[28]  
Ledoux M., 1991, Ergebnisse der Mathematik und ihrer Grenzgebiete (3). Results in Mathematics and Related Areas (3)
[29]  
LORENZ EN, 1969, J ATMOS SCI, V26, P636, DOI 10.1175/1520-0469(1969)26<636:APARBN>2.0.CO
[30]  
2