scad – Optimization Online

A TVSCAD approach for image deblurring with impulsive noise

Published: 2017/02/08

Nonsmooth Optimization alternating direction method of multipliers, dc programming, deblurring, impulsive noise, kl function, l1-norm, regularization, scad, total variation

We consider image deblurring problem in the presence of impulsive noise. It is known that \emph{total variation} (TV) regularization with L1-norm penalized data fitting (TVL1 for short) works reasonably well only when the level of impulsive noise is relatively low. For high level impulsive noise, TVL1 works poorly. The reason is that all data, both … Read more

Convergence Analysis of ISTA and FISTA for “Strongly + Semi” Convex Programming

Published: 2016/06/22

Ke Guo

Xiao-Ming Yuan

Shangzhi Zeng

Convex Optimization convergence rate, fista, iteratively shrinkage/thresholding algorithm, nonconvex penalty, scad, semiconvex

The iterative shrinkage/thresholding algorithm (ISTA) and its faster version FISTA have been widely used in the literature. In this paper, we consider general versions of the ISTA and FISTA in the more general “strongly + semi” convex setting, i.e., minimizing the sum of a strongly convex function and a semiconvex function; and conduct convergence analysis … Read more