Sampling Requirements for Stable Autoregressive Estimation

Abstract

We consider the problem of estimating the parameters of a linear univariate autoregressive model with sub-Gaussian innovations from a limited sequence of consecutive observations. Assuming that the parameters are compressible, we analyze the performance of the ${\ell }_1$-regularized least squares as well as a greedy estimator of the parameters and characterize the sampling trade-offs required for stable recovery in the non-asymptotic regime. In particular, we show that for a fixed sparsity level, stable recovery of AR parameters is possible when the number of samples scale sub-linearly with the AR order. Our results improve over existing sampling complexity requirements in AR estimation using the LASSO, when the sparsity level scales faster than the square root of the model order. We further derive sufficient conditions on the sparsity level that guarantee the minimax optimality of the ${\ell }_1$-regularized least squares estimate. Applying these techniques to simulated data as well as real-world datasets from crude oil prices and traffic speed data confirm our predicted theoretical performance gains in terms of estimation accuracy and model selection.

References in corpus (6)

• High-dimensional graphs and variable selection with the Lasso
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional regression with noisy and missing data: Provable guarantees with nonconvexity
• Regularized estimation in sparse high-dimensional time series models
• Order selection for same-realization predictions in autoregressive processes
• Simultaneous sparse model selection and coefficient estimation for heavy-tailed autoregressive processes

Cited by in corpus (1)

• Non-Asymptotic Guarantees for Reliable Identification of Granger Causality via the LASSO