A Unified Framework for Change Point Detection in High-Dimensional Linear Models

DOI10.5705/SS.202021.0309arXiv2207.09007OpenAlexW4287831325WikidataQ114013777 ScholiaQ114013777MaRDI QIDQ6069892FDOQ6069892

Authors: Yue Bai, Abolfazl Safikhani 

Publication date: 17 November 2023

Published in: STATISTICA SINICA (Search for Journal in Brave)

Abstract: In recent years, change point detection for high dimensional data has become increasingly important in many scientific fields. Most literature develop a variety of separate methods designed for specified models (e.g. mean shift model, vector auto-regressive model, graphical model). In this paper, we provide a unified framework for structural break detection which is suitable for a large class of models. Moreover, the proposed algorithm automatically achieves consistent parameter estimates during the change point detection process, without the need for refitting the model. Specifically, we introduce a three-step procedure. The first step utilizes the block segmentation strategy combined with a fused lasso based estimation criterion, leads to significant computational gains without compromising the statistical accuracy in identifying the number and location of the structural breaks. This procedure is further coupled with hard-thresholding and exhaustive search steps to consistently estimate the number and location of the break points. The strong guarantees are proved on both the number of estimated change points and the rates of convergence of their locations. The consistent estimates of model parameters are also provided. The numerical studies provide further support of the theory and validate its competitive performance for a wide range of models. The developed algorithm is implemented in the R package LinearDetect.

Full work available at URL: https://arxiv.org/abs/2207.09007

zbMATH Keywords

high-dimensional datalinear modelstructural breakspiecewise stationarityfused Lassoblock segmentation

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Estimating the number of clusters in a data set via the gap statistic
• Regularized estimation in sparse high-dimensional time series models
• Tail-greedy bottom-up data decompositions and fast multiple change-point detection
• Simultaneous analysis of Lasso and Dantzig selector
• High-dimensional graphs and variable selection with the Lasso
• Sparsity and Smoothness Via the Fused Lasso
• Title not available (Why is that?)
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Properties and refinements of the fused Lasso
• Change-point detection in panel data via double CUSUM statistic
• Network vector autoregression
• Structural breaks in time series
• Model selection and estimation in the Gaussian graphical model
• Title not available (Why is that?)
• Optimal detection of changepoints with a linear computational cost
• A nonparametric approach for multiple change point analysis of multivariate data
• Multiple Change-Point Estimation With a Total Variation Penalty
• Multiple-Change-Point Detection for High Dimensional Time Series via Sparsified Binary Segmentation
• Multiscale Change Point Inference
• SLEX Analysis of Multivariate Nonstationary Time Series
• Structural Break Estimation for Nonstationary Time Series Models
• Detection of abrupt changes: theory and application
• The adaptive and the thresholded Lasso for potentially misspecified models (and a lower bound for the Lasso)
• High-dimensional covariance estimation based on Gaussian graphical models
• Financial Surveillance
• Consistent tuning parameter selection in high dimensional sparse linear regression
• Change point estimation in high dimensional Markov random-field models
• Detecting and dating structural breaks in functional data without dimension reduction
• Estimating networks with jumps
• Consistent multiple changepoint estimation with fused Gaussian graphical models
• Unsupervised self-normalized change-point testing for time series
• A Unified Data-Adaptive Framework for High Dimensional Change Point Detection
• Joint Structural Break Detection and Parameter Estimation in High-Dimensional Nonstationary VAR Models
• Self-normalized sequential change-point detection
• Change-point computation for large graphical models: a scalable algorithm for Gaussian graphical models with change-points
• Large-Scale Multi-Stream Quickest Change Detection via Shrinkage Post-Change Estimation
• Multiple Change Points Detection in Low Rank and Sparse High Dimensional Vector Autoregressive Models

Cited In (4)

• Change-point detection in high-dimensional covariance structure
• Inference for change points in high-dimensional data via selfnormalization
• Sequential change point detection for high‐dimensional data using nonconvex penalized quantile regression
• Consistent two‐stage multiple change‐point detection in linear models

This page was built for publication: A Unified Framework for Change Point Detection in High-Dimensional Linear Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6069892)