The group fused Lasso for multiple change-point detection

Abstract

We present the group fused Lasso for detection of multiple change-points shared by a set of co-occurring one-dimensional signals. Change-points are detected by approximating the original signals with a constraint on the multidimensional total variation, leading to piecewise-constant approximations. Fast algorithms are proposed to solve the resulting optimization problems, either exactly or approximately. Conditions are given for consistency of both algorithms as the number of signals increases, and empirical evidence is provided to support the results on simulated and array comparative genomic hybridization data.

References in corpus (3)

• Pathwise coordinate optimization
• Properties and refinements of the fused lasso
• Detection and localization of change-points in high-dimensional network traffic data

Cited by in corpus (37)

• A Kernel Multiple Change-point Algorithm via Model Selection
• Regularized Estimation of Piecewise Constant Gaussian Graphical Models: The Group-Fused Graphical Lasso
• Homogeneity and change-point detection tests for multivariate data using rank statistics
• Performance evaluation of DNA copy number segmentation methods
• ecp: An R Package for Nonparametric Multiple Change Point Analysis of Multivariate Data
• Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms
• Statistically and Computationally Efficient Change Point Localization in Regression Settings
• Multiple Changepoint Estimation in High-Dimensional Gaussian Graphical Models
• Towards Human Body-Part Learning for Model-Free Gait Recognition
• A Nonparametric Approach for Multiple Change Point Analysis of Multivariate Data
• On-the-fly Approximation of Multivariate Total Variation Minimization
• Panel data segmentation under finite time horizon
• anomaly : Detection of Anomalous Structure in Time Series Data
• Valid and Exact Statistical Inference for Multi-dimensional Multiple Change-Points by Selective Inference
• Element-wise estimation error of a total variation regularized estimator for change point detection
• Cognitive Deep Machine Can Train Itself
• Convergence rates for smooth k-means change-point detection
• Frank-Wolfe Methods with an Unbounded Feasible Region and Applications to Structured Learning
• History Playground: A Tool for Discovering Temporal Trends in Massive Textual Corpora
• Detecting Changes in Time Series Data using Volatility Filters
• ABM: an automatic supervised feature engineering method for loss based models based on group and fused lasso
• An Algorithm for Graph-Fused Lasso Based on Graph Decomposition
• Algorithm for overlapping estimation of common change-sets in spatial data of fixed size
• Learning the intensity of time events with change-points
• Genomic Region Detection via Spatial Convex Clustering
• Multi-dimensional signal approximation with sparse structured priors using split Bregman iterations
• Multi-regime analysis for computer vision-based traffic surveillance using a change-point detection algorithm
• Change Point Analysis of Multivariate Data: Using Multivariate Rank-based Distribution-free Nonparametric Testing via Measure Transportation with Applications in Tumor Microarrays and Dementia
• Fusion regression methods with repeated functional data
• Sparse Group Fused Lasso for Model Segmentation
• Reconstructing DNA copy number by joint segmentation of multiple sequences
• Image edges resolved well when using an overcomplete piecewise-polynomial model
• Unsupervised Action Proposal Ranking through Proposal Recombination
• Solving the L1 regularized least square problem via a box-constrained smooth minimization
• Probabilistic Segmentation via Total Variation Regularization
• A breakpoint detection error function for segmentation model selection and evaluation
• An Algorithmic Theory of Dependent Regularizers, Part 1: Submodular Structure