Estimation and Selection Properties of the LAD Fused Lasso Signal Approximator

TL;DR

This paper explores the properties of a robust LAD-based fused lasso method for signal approximation, demonstrating its consistency, sign recovery, and providing an unbiased degrees of freedom estimator, with validation through simulations and real data.

Contribution

It introduces the LAD fused lasso signal approximator, analyzing its asymptotic properties and developing an unbiased degrees of freedom estimator for robust signal processing.

Findings

LAD-FLSA is estimation consistent under certain conditions.

The method achieves sign consistency for sparse signals.

An unbiased degrees of freedom estimator improves model tuning.

Abstract

The fused lasso is an important method for signal processing when the hidden signals are sparse and blocky. It is often used in combination with the squared loss function. However, the squared loss is not suitable for heavy tail error distributions nor is robust against outliers which arise often in practice. The least absolute deviations (LAD) loss provides a robust alternative to the squared loss. In this paper, we study the asymptotic properties of the fused lasso estimator with the LAD loss for signal approximation. We refer to this estimator as the LAD fused lasso signal approximator, or LAD-FLSA. We investigate the estimation consistency properties of the LAD-FLSA and provide sufficient conditions under which the LAD-FLSA is sign consistent. We also construct an unbiased estimator for the degrees of freedom of the LAD-FLSA for any given tuning parameters. Both simulation studies and real data analysis are conducted to illustrate the performance of the LAD-FLSA and the effect of the unbiased estimator of the degrees of freedom.