Localizing Changes in High-Dimensional Vector Autoregressive Processes
arXiv:1909.06359
Abstract
Autoregressive models capture stochastic processes in which past realizations determine the generative distribution of new data; they arise naturally in a variety of industrial, biomedical, and financial settings. A key challenge when working with such data is to determine when the underlying generative model has changed, as this can offer insights into distinct operating regimes of the underlying system. This paper describes a novel dynamic programming approach to localizing changes in high-dimensional autoregressive processes and associated error rates that improve upon the prior state of the art. When the model parameters are piecewise constant over time and the corresponding process is piecewise stable, the proposed dynamic programming algorithm consistently localizes change points even as the dimensionality, the sparsity of the coefficient matrices, the temporal spacing between two consecutive change points, and the magnitude of the difference of two consecutive coefficient matrices are allowed to vary with the sample size. Furthermore, the accuracy of initial, coarse change point localization estimates can be boosted via a computationally-efficient refinement algorithm that provably improves the localization error rate. Finally, a comprehensive simulation experiments and a real data analysis are provided to show the numerical superiority of our proposed methods.
arXiv comment53 pages; 4 figure
References in corpus (18)
- Optimal detection of changepoints with a linear computational cost
- Simultaneous analysis of Lasso and Dantzig selector
- On the conditions used to prove oracle results for the Lasso
- High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
- Causal Network Inference via Group Sparse Regularization
- Change-point detection in panel data via double CUSUM statistic
- Covariance matrix estimation for stationary time series
- A Direct Estimation of High Dimensional Stationary Vector Autoregressions
- Factor modeling for high-dimensional time series: Inference for the number of factors
- Principal component analysis for second-order stationary vector time series
- Testing for high-dimensional white noise using maximum cross-correlations
- Optimal Change Point Detection and Localization in Sparse Dynamic Networks
- Computationally efficient change point detection for high-dimensional regression
- Optimal Covariance Change Point Localization in High Dimension
- Statistically and Computationally Efficient Change Point Localization in Regression Settings
- Partial Coherence Estimation via Spectral Matrix Shrinkage under Quadratic Loss
- Bayesian Structure Learning for Stationary Time Series
- Spectral Analysis of High-dimensional Time Series