New Risk Bounds for 2D Total Variation Denoising

Sabyasachi Chatterjee, Subhajit Goswami

Research output: Contribution to journalArticlepeer-review

Abstract

2D Total Variation Denoising (TVD) is a widely used technique for image denoising. It is also an important nonparametric regression method for estimating functions with heterogenous smoothness. Recent results have shown the TVD estimator to be nearly minimax rate optimal for the class of functions with bounded variation. In this paper, we complement these worst case guarantees by investigating the adaptivity of the TVD estimator to functions which are piecewise constant on axis aligned rectangles. We rigorously show that, when the truth is piecewise constant with few pieces, the ideally tuned TVD estimator performs better than in the worst case. We also study the issue of choosing the tuning parameter. In particular, we propose a fully data driven version of the TVD estimator which enjoys similar worst case risk guarantees as the ideally tuned TVD estimator.

Original languageEnglish (US)
Article number9354825
Pages (from-to)4060-4091
Number of pages32
JournalIEEE Transactions on Information Theory
Volume67
Issue number6
DOIs
StatePublished - Jun 2021

Keywords

  • Nonparametric regression
  • estimation of piecewise constant functions
  • gaussian width
  • recursive partitioning
  • tangent cone
  • total variation denoising
  • tuning free estimation

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Fingerprint

Dive into the research topics of 'New Risk Bounds for 2D Total Variation Denoising'. Together they form a unique fingerprint.

Cite this