Finite sample theory for high-dimensional functional/scalar time series with applications

Statistical analysis of high-dimensional functional times series arises in various applications. Under this scenario, in addition to the intrinsic infinite-dimensionality of functional data, the number of functional variables can grow with the number of serially dependent observations. In this paper, we focus on the theoretical analysis of relevant estimated cross-(auto)covariance terms between two multivariate functional time series or a mixture of multivariate functional and scalar time series beyond the Gaussianity assumption. We introduce a new perspective on dependence by proposing functional cross-spectral stability measure to characterize the effect of dependence on these estimated cross terms, which are essential in the estimates for additive functional linear regressions. With the proposed functional cross-spectral stability measure, we develop useful concentration inequalities for estimated cross-(auto)covariance matrix functions to accommodate more general sub-Gaussian functional linear processes and, furthermore, establish finite sample theory for relevant estimated terms under a commonly adopted functional principal component analysis framework. Using our derived non-asymptotic results, we investigate the convergence properties of the regularized estimates for two additive functional linear regression applications under sparsity assumptions including functional linear lagged regression and partially functional linear regression in the context of high-dimensional functional/scalar time series.

[1]  Cauchy-Schwarz Inequalities Associated with Positive Semide niteMatricesRoger , 2000 .

[2]  Siegfried Hörmann,et al.  On the Prediction of Stationary Functional Time Series , 2012, 1208.2892.

[3]  Yannig Goude,et al.  Modeling and Forecasting Daily Electricity Load Curves: A Hybrid Approach , 2013, 1611.08632.

[4]  Gareth M. James,et al.  Functional additive regression , 2015, 1510.04064.

[5]  P. Kokoszka,et al.  Weakly dependent functional data , 2010, 1010.0792.

[6]  Xinghao Qiao,et al.  Functional Graphical Models , 2018, Journal of the American Statistical Association.

[7]  Joel L. Horowitz,et al.  Methodology and convergence rates for functional linear regression , 2007, 0708.0466.

[8]  Garvesh Raskutti,et al.  Non-Parametric Sparse Additive Auto-Regressive Network Models , 2018, IEEE Transactions on Information Theory.

[9]  Fang Yao,et al.  Partially functional linear regression in high dimensions , 2016 .

[10]  George Michailidis,et al.  Regularized Estimation and Testing for High-Dimensional Multi-Block Vector-Autoregressive Models , 2017, J. Mach. Learn. Res..

[11]  R. Horn,et al.  Cauchy-Schwarz inequalities associated with positive semidefinite matrices , 1990 .

[12]  Wolfgang Jank,et al.  FUNCTIONAL RESPONSE ADDITIVE MODEL ESTIMATION WITH ONLINE VIRTUAL STOCK MARKETS , 2014, 1502.00818.

[13]  Denis Bosq,et al.  Linear Processes in Function Spaces , 2000 .

[14]  R. Tsay,et al.  High-dimensional Linear Regression for Dependent Data with Applications to Nowcasting , 2017, Statistica Sinica.

[15]  Ruiyan Luo,et al.  Function-on-Function Linear Regression by Signal Compression , 2017 .

[16]  An autocovariance-based learning framework for high-dimensional functional time series , 2020, 2008.12885.

[17]  Siegfried Hörmann,et al.  Estimation in Functional Lagged Regression , 2015 .

[18]  Hansheng Wang,et al.  Banded spatio-temporal autoregressions , 2018, Journal of Econometrics.

[19]  Piotr Kokoszka,et al.  Testing stationarity of functional time series , 2014 .

[20]  Victor M. Panaretos,et al.  Fourier analysis of stationary time series in function space , 2013, 1305.2073.

[21]  Robert Tibshirani,et al.  STANDARDIZATION AND THE GROUP LASSO PENALTY. , 2012, Statistica Sinica.

[22]  Po-Ling Loh,et al.  High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity , 2011, NIPS.

[23]  Shaojun Guo,et al.  High Dimensional and Banded Vector Autoregressions , 2015, 1502.07831.

[24]  B. Nan,et al.  Estimation of large covariance and precision matrices from temporally dependent observations , 2014, The Annals of Statistics.

[25]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[26]  Sumanta Basu,et al.  Large Spectral Density Matrix Estimation by Thresholding , 2018, 1812.00532.

[27]  Fang Yao,et al.  Hypothesis Testing in Large-scale Functional Linear Regression , 2021 .

[28]  Han Lin Shang,et al.  Long-Range Dependent Curve Time Series , 2020, Journal of the American Statistical Association.

[29]  Methodology and Convergence Rates for Functional Time Series Regression , 2016, 1612.07197.

[30]  Kam Chung Wong,et al.  LASSO GUARANTEES FOR β-MIXING HEAVY TAILED TIME SERIES ∗ By , 2019 .

[31]  M. Rudelson,et al.  Hanson-Wright inequality and sub-gaussian concentration , 2013 .

[32]  Shaojun Guo,et al.  On consistency and sparsity for high-dimensional functional time series with application to autoregressions , 2020, Bernoulli.

[33]  Y. Wu,et al.  Performance bounds for parameter estimates of high-dimensional linear models with correlated errors , 2016 .

[34]  Qiwei Yao,et al.  Identifying the finite dimensionality of curve time series , 2010, 1211.2522.

[35]  Jianfeng Yao,et al.  On testing for high-dimensional white noise , 2018, The Annals of Statistics.

[36]  George Michailidis,et al.  Regularized Estimation of High-dimensional Factor-Augmented Vector Autoregressive (FAVAR) Models , 2020, J. Mach. Learn. Res..

[37]  Clifford Lam,et al.  Factor modeling for high-dimensional time series: inference for the number of factors , 2012, 1206.0613.

[38]  Kshitij Khare,et al.  High-Dimensional Posterior Consistency in Bayesian Vector Autoregressive Models , 2018, Journal of the American Statistical Association.

[39]  G. Michailidis,et al.  Regularized estimation in sparse high-dimensional time series models , 2013, 1311.4175.