Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models

被引:0
|
作者
Huang, Biwei [1 ]
Zhang, Kun [1 ]
Gong, Mingming [1 ,2 ]
Glymour, Clark [1 ]
机构
[1] Carnegie Mellon Univ, Dept Philosophy, Pittsburgh, PA 15213 USA
[2] Univ Pittsburgh, Dept Biomed Informat, Pittsburgh, PA USA
基金
美国国家科学基金会; 美国国家卫生研究院;
关键词
INFERENCE; NETWORKS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting the values of variables of interest, both of which are particularly challenging in such nonstationary environments. In this paper, we study causal discovery and forecasting for nonstationary time series. By exploiting a particular type of state-space model to represent the processes, we show that nonstationarity helps to identify causal structure and that forecasting naturally benefits from learned causal knowledge. Specifically, we allow changes in both causal strengths and noise variances in the nonlinear state-space models, which, interestingly, renders both the causal structure and model parameters identifiable. Given the causal model, we treat forecasting as a problem in Bayesian inference in the causal model, which exploits the time-varying property of the data and adapts to new observations in a principled manner. Experimental results on synthetic and real-world data sets demonstrate the efficacy of the proposed methods.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] PRICE FORECASTING WITH STATE-SPACE MODELS OF NONSTATIONARY TIME-SERIES - CASE OF THE JAPANESE SALMON MARKET
    VUKINA, T
    ANDERSON, JL
    COMPUTERS & MATHEMATICS WITH APPLICATIONS, 1994, 27 (05) : 45 - 62
  • [2] FAST LIKELIHOOD EVALUATION AND PREDICTION FOR NONSTATIONARY STATE-SPACE MODELS
    DEJONG, P
    CHUCHUNLIN, S
    BIOMETRIKA, 1994, 81 (01) : 133 - 142
  • [3] MACROECONOMIC FORECASTING EXPERIENCE WITH BALANCED STATE-SPACE MODELS
    MITTNIK, S
    INTERNATIONAL JOURNAL OF FORECASTING, 1990, 6 (03) : 337 - 348
  • [4] SPECTRAL REPRESENTATION OF NONSTATIONARY SYSTEMS IN THE STATE-SPACE
    MILOV, LT
    SOLODOVNIKOV, VV
    ENGINEERING CYBERNETICS, 1979, 17 (05): : 133 - 139
  • [6] Recurrent dictionary learning for state-space models with an application in stock forecasting
    Sharma, Shalini
    Elvira, Victor
    Chouzenoux, Emilie
    Majumdar, Angshul
    NEUROCOMPUTING, 2021, 450 : 1 - 13
  • [7] Univariate and multivariate forecasting of tourism demand using state-space models
    Jorge-Gonzalez, Elisa
    Gonzalez-Davila, Enrique
    Martin-Rivero, Raquel
    Lorenzo-Diaz, Domingo
    TOURISM ECONOMICS, 2020, 26 (04) : 598 - 621
  • [8] Discriminative State-Space Models
    Kuznetsov, Vitaly
    Mohri, Mehryar
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [9] Dynamic state-space models
    Guo, WS
    JOURNAL OF TIME SERIES ANALYSIS, 2003, 24 (02) : 149 - 158
  • [10] Structured state-space models are deep Wiener modelsStructured state-space models are deep Wiener models
    Bonassi, Fabio
    Andersson, Carl
    Mattsson, Per
    Schon, Thomas B.
    IFAC PAPERSONLINE, 2024, 58 (15): : 247 - 252