EcoSta 2022: Start Registration
View Submission - EcoSta2022
A0359
Title: SARMA: A computationally scalable high-dimensional time series model Authors:  Feiqing Huang - University of Hong Kong (Hong Kong) [presenting]
Yao Zheng - University of Connecticut (United States)
Kexin Lu - University of Hong Kong (Hong Kong)
Guodong Li - University of Hong Kong (Hong Kong)
Abstract: A novel parametric infinite-order vector autoregressive model is introduced. As a variant of the vector autoregressive moving average (ARMA) model, it not only inherits desirable properties such as parsimony and rich temporal dependence structures, but also avoids two well-known drawbacks of the former: (i) non-identifiability and (ii) computational intractability even for moderate-dimensional data. Moreover, its parameter estimation is scalable with respect to the complexity of temporal dependence, namely the number of decay patterns constituting the autoregressive structure; hence it is called the scalable ARMA (SARMA) model. In the high-dimensional setup, we further impose a low-Tucker-rank assumption on the coefficient tensor of the proposed model. The resulting model has the form of a regression with embedded dynamic factors and hence can be especially suited for financial and economic data. Non-asymptotic error bounds for the proposed estimator are derived, and a tractable alternating least squares algorithm is developed. Theoretical and computational properties of the proposed method are verified by simulation studies, and the advantages over existing methods are illustrated in real applications.