Regularizing with Bregman-Moreau envelopes
arXiv:1705.06019 · doi:10.1137/17M1130745
Abstract
Moreau's seminal paper, introducing what is now called the Moreau envelope and the proximity operator (also known as the proximal mapping), appeared in 1965. The Moreau envelope of a given convex function provides a regularized version which has additional desirable properties such as differentiability and full domain. Fifty years ago, Attouch proposed using the Moreau envelope for regularization. Since then, this branch of convex analysis has developed in many fruitful directions. In 1967, Bregman introduced what is nowadays known as the Bregman distance as a measure of discrepancy between two points generalizing the square of the Euclidean distance. Proximity operators based on the Bregman distance have become a topic of significant research as they are useful in the algorithmic solution of optimization problems. More recently, in 2012, Kan and Song studied regularization aspects of the left Bregman-Moreau envelope even for nonconvex functions. In this paper, we complement previous works by analyzing the left and right Bregman-Moreau envelopes and by providing additional asymptotic results. Several examples are provided.
References in corpus (1)
Cited by in corpus (8)
- A Bregman forward-backward linesearch algorithm for nonconvex composite optimization: superlinear convergence to nonisolated local minima
- Stochastic model-based minimization under high-order growth
- Multi-block Bregman proximal alternating linearized minimization and its application to orthogonal nonnegative matrix factorization
- A Primal-Dual Smoothing Framework for Max-Structured Non-Convex Optimization
- Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
- Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions
- Dualities for non-Euclidean smoothness and strong convexity under the light of generalized conjugacy
- Generalized Bregman envelopes and proximity operators