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

[21] Predictiuo of multi-dimensijnal non-stationary time series using neuromodeling
Epikhin, Aleksey, I
Khekert, Evgeniy, V
Kondratyev, Sergey, I
MARINE INTELLECTUAL TECHNOLOGIES, 2020, (04): : 23 - 27
[22] Wavelet Transform Application for/in Non-Stationary Time-Series Analysis: A Review
Rhif, Manel
Ben Abbes, Ali
Farah, Imed Riadh
Martinez, Beatriz
Sang, Yanfang
APPLIED SCIENCES-BASEL, 2019, 9 (07):
[23] Characterizing time-resolved stochasticity in non-stationary time series
Rahvar, Sepehr
Reihani, Erfan S.
Golestani, Amirhossein N.
Hamounian, Abolfazl
Aghaei, Fatemeh
Sahimi, Muhammad
Manshour, Pouya
Palus, Milan
Feudel, Ulrike
Freund, Jan A.
Lehnertz, Klaus
Rings, Thorsten
Tabar, M. Reza Rahimi
CHAOS SOLITONS & FRACTALS, 2024, 185
[24] A Bayesian nonparametric Markovian model for non-stationary time series
Maria DeYoreo
Athanasios Kottas
Statistics and Computing, 2017, 27 : 1525 - 1538
[25] A Bayesian nonparametric Markovian model for non-stationary time series
DeYoreo, Maria
Kottas, Athanasios
STATISTICS AND COMPUTING, 2017, 27 (06) : 1525 - 1538
[26] Modelling customer demand for mobile value-added services: non-stationary time series models or neural networks time series analysis?
Vaghefzadeh M.H.
Karimi B.
Ahmadi A.
International Journal of Industrial and Systems Engineering, 2023, 43 (04) : 555 - 581
[27] Comparative Analysis of ARIMA and Artificial Neural Network Techniques for Forecasting Non-Stationary Agricultural Output Time Series
Awe, Olushina Olawale
Dias, Ronaldo
AGRIS ON-LINE PAPERS IN ECONOMICS AND INFORMATICS, 2022, 14 (04) : 3 - 9
[28] A Moment Cross Predictor For Non-stationary Mobile Traffic Forecasting
Ge, Yunfeng
Zhang, Yingxin
Shi, Keyi
Li, Hongyan
2024 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA, ICCC, 2024,
[29] Information Theory for Non-Stationary Processes with Stationary Increments
Granero-Belinchon, Carlos
Roux, Stephane G.
Garnier, Nicolas B.
ENTROPY, 2019, 21 (12)
[30] Principles and algorithms for forecasting groups of time series: Locality and globality
Montero-Manso, Pablo
Hyndman, Rob J.
INTERNATIONAL JOURNAL OF FORECASTING, 2021, 37 (04) : 1632 - 1653

← 1 2 3 4 5 →