Properties and refinements of the fused lasso

Abstract

We consider estimating an unknown signal, both blocky and sparse, which is corrupted by additive noise. We study three interrelated least squares procedures and their asymptotic properties. The first procedure is the fused lasso, put forward by Friedman et al. [Ann. Appl. Statist. 1 (2007) 302--332], which we modify into a different estimator, called the fused adaptive lasso, with better properties. The other two estimators we discuss solve least squares problems on sieves; one constrains the maximal ${\ell }_1$ norm and the maximal total variation seminorm, and the other restricts the number of blocks and the number of nonzero coordinates of the signal. We derive conditions for the recovery of the true block partition and the true sparsity patterns by the fused lasso and the fused adaptive lasso, and we derive convergence rates for the sieve estimators, explicitly in terms of the constraining parameters.

Published in at http://dx.doi.org/10.1214/08-AOS665 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (4)

• Pathwise coordinate optimization
• Sharp thresholds for high-dimensional and noisy recovery of sparsity
• Consistencies and rates of convergence of jump-penalized least squares estimators
• Best subset selection, persistence in high-dimensional statistical learning and optimization under $l_1$ constraint

Cited by in corpus (16)

• Wild binary segmentation for multiple change-point detection
• The group fused Lasso for multiple change-point detection
• The screening and ranking algorithm to detect DNA copy number variations
• Regularization with the Smooth-Lasso procedure
• Bayesian Fused Lasso regression for dynamic binary networks
• A coordinate-wise optimization algorithm for the Fused Lasso
• Valid Post-Detection Inference for Change Points Identified Using Trend Filtering
• T-LoHo: A Bayesian Regularization Model for Structured Sparsity and Smoothness on Graphs
• Iterative Alpha Expansion for estimating gradient-sparse signals from linear measurements
• Exponential Family Trend Filtering on Lattices
• Change-point detection in a linear model by adaptive fused quantile method
• Sparsity-Assisted Signal Denoising and Pattern Recognition in Time-Series Data
• Scalable Inference of Sparsely-changing Markov Random Fields with Strong Statistical Guarantees
• Tree-Projected Gradient Descent for Estimating Gradient-Sparse Parameters on Graphs
• Interquantile Shrinkage in Spatial Quantile Autoregressive Regression models
• Joint Linear Trend Recovery Using L1 Regularization