Approximation Theory of Total Variation Minimization for Data Completion

TL;DR

This paper analyzes the error bounds of total variation minimization for data completion from partial, random observations, connecting discrete models to underlying function approximation and sparse gradient recovery.

Contribution

It provides theoretical error estimates for TV-based data restoration from partial samples, bridging discrete models and function approximation.

Findings

Error bounds for TV minimization from random samples

Connection between discrete TV models and function approximation

Insights into sparse gradient recovery

Abstract

Total variation (TV) minimization is one of the most important techniques in modern signal/image processing, and has wide range of applications. While there are numerous recent works on the restoration guarantee of the TV minimization in the framework of compressed sensing, there are few works on the restoration guarantee of the restoration from partial observations. This paper is to analyze the error of TV based restoration from random entrywise samples. In particular, we estimate the error between the underlying original data and the approximate solution that interpolates (or approximates with an error bound depending on the noise level) the given data that has the minimal TV seminorm among all possible solutions. Finally, we further connect the error estimate for the discrete model to the sparse gradient restoration problem and to the approximation to the underlying function from which the underlying true data comes.