Smoothness-Penalized Deconvolution (SPeD) of a Density Estimate

TL;DR

This paper introduces a smoothness-penalized deconvolution estimator for density estimation from contaminated data, providing theoretical guarantees and practical spline-based approximation methods, outperforming traditional kernel techniques.

Contribution

It establishes asymptotic guarantees for the smoothness-penalized deconvolution estimator, including consistency and convergence rates, with broader applicability than kernel methods.

Findings

Achieves consistency in mean integrated squared error.

Derives convergence rates for Gaussian, Cauchy, and Laplace errors.

Provides a spline-based approximation method reducing to quadratic programming.

Abstract

This paper addresses the deconvolution problem of estimating a square-integrable probability density from observations contaminated with additive measurement errors having a known density. The estimator begins with a density estimate of the contaminated observations and minimizes a reconstruction error penalized by an integrated squared $m$-th derivative. Theory for deconvolution has mainly focused on kernel- or wavelet-based techniques, but other methods including spline-based techniques and this smoothness-penalized estimator have been found to outperform kernel methods in simulation studies. This paper fills in some of these gaps by establishing asymptotic guarantees for the smoothness-penalized approach. Consistency is established in mean integrated squared error, and rates of convergence are derived for Gaussian, Cauchy, and Laplace error densities, attaining some lower bounds already in the literature. The assumptions are weak for most results; the estimator can be used with a broader class of error densities than the deconvoluting kernel. Our application example estimates the density of the mean cytotoxicity of certain bacterial isolates under random sampling; this mean cytotoxicity can only be measured experimentally with additive error, leading to the deconvolution problem. We also describe a method for approximating the solution by a cubic spline, which reduces to a quadratic program.