A new envelope function for nonsmooth DC optimization

Abstract

Difference-of-convex (DC) optimization problems are shown to be equivalent to the minimization of a Lipschitz-differentiable "envelope". A gradient method on this surrogate function yields a novel (sub)gradient-free proximal algorithm which is inherently parallelizable and can handle fully nonsmooth formulations. Newton-type methods such as L-BFGS are directly applicable with a classical linesearch. Our analysis reveals a deep kinship between the novel DC envelope and the forward-backward envelope, the former being a smooth and convexity-preserving nonlinear reparametrization of the latter.

References in corpus (6)

• Generalized power method for sparse principal component analysis
• Forward-backward quasi-Newton methods for nonsmooth optimization problems
• Forward-backward envelope for the sum of two nonconvex functions: Further properties and nonmonotone line-search algorithms
• Douglas-Rachford splitting and ADMM for nonconvex optimization: tight convergence results
• Accelerating the DC algorithm for smooth functions
• Newton-type Alternating Minimization Algorithm for Convex Optimization

Cited by in corpus (2)

• Lasry-Lions Envelopes and Nonconvex Optimization: A Homotopy Approach
• A mirror inertial forward-reflected-backward splitting: Global convergence and linesearch extension beyond convexity and Lipschitz smoothness