The Bregman proximal average

DOI10.1137/21M1442474MaRDI QIDQ5081784zbMATH OpenOpenAlexFDO

Authors Heinz H. Bauschke, Xianfu Wang

Publication date 17 June 2022

Published in SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2108.11440

zbMATH Keywords

\(\phi\)-prox-bounded functionBregman distanceBregman envelopeBregman proximal averageBregman proximal mappingcombettes-reyes anisotropic envelopecombettes-reyes proximal mappingepi-convergenceLegendre function

Mathematics Subject Classification ID

Convexity of real functions of several variables, generalizations (26B25) Means (26E60) Monotone operators and generalizations (47H05) Set-valued and variational analysis (49J53) Axiomatic and generalized convexity (52A01) Nonconvex programming, global optimization (90C26)

Abstract: We provide a proximal average with repect to a $1$-coercive Legendre function. In the sense of Bregman distance, the Bregman envelope of the proximal average is a convex combination of Bregman envelopes of individual functions. The Bregman proximal mapping of the average is a convex combination of convexified proximal mappings of individual functions. Techniques from variational analysis provide the keys for the Bregman proximal average.

Recommendations

• The Proximal Average: Basic Theory
• A proximal average for prox-bounded functions
• The Moreau envelope function and proximal mapping in the sense of the Bregman distance
• Proximal averages for minimization of entropy functionals
• Convexity of the proximal average

Cites work

• A proximal average for nonconvex functions: a proximal stability perspective
• A proximal average for prox-bounded functions
• Approximation and regularization of arbitrary functions in Hilbert spaces by the Lasry-Lions method
• Bregman distances and Chebyshev sets
• Bregman Monotone Optimization Algorithms
• Bregman proximal mappings and Bregman-Moreau envelopes under relative prox-regularity
• Compensated convexity methods for approximations and interpolations of sampled functions in Euclidean spaces: theoretical foundations
• Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
• Convex Analysis
• Convex analysis and monotone operator theory in Hilbert spaces
• Convex analysis and nonlinear optimization. Theory and examples.
• Convex functions. Constructions, characterizations and counterexamples
• How to Transform One Convex Function Continuously into Another
• scientific article; zbMATH DE number 5077050 (Why is no real title available?)
• scientific article; zbMATH DE number 46303 (Why is no real title available?)
• scientific article; zbMATH DE number 490143 (Why is no real title available?)
• scientific article; zbMATH DE number 1046019 (Why is no real title available?)
• Information, divergence and risk for binary experiments
• Iterative averaging of entropic projections for solving stochastic convex feasibility problems
• Joint and separate convexity of the Bregman distance.
• Minimax monotonicity
• Moreau's decomposition in Banach spaces
• On linear convergence of non-Euclidean gradient methods without strong convexity and Lipschitz gradient continuity
• Projection and proximal point methods: Convergence results and counterexamples.
• Proximal mappings
• Proximal minimization algorithm with \(D\)-functions
• Proximité et dualité dans un espace hilbertien
• Quelques propriétés des opérateurs angle-bornes et n-cycliquement monotones
• Regularizing with Bregman-Moreau envelopes
• Strongly convex functions, Moreau envelopes, and the generic nature of convex functions with strong minimizers
• The kernel average for two convex functions and its application to the extension and representation of monotone operators
• The Moreau envelope function and proximal mapping in the sense of the Bregman distance
• The Moreau envelope function and proximal mapping with respect to the Bregman distances in Banach spaces
• The proximal average for saddle functions and its symmetry properties with respect to partial and saddle conjugacy
• The Proximal Average: Basic Theory
• The resolvent average of monotone operators: dominant and recessive properties
• The resolvent average on symmetric cones
• Totally convex functions for fixed points computation and infinite dimensional optimization
• Variational Analysis
• Warped proximal iterations for monotone inclusions
• What is the Subdifferential of the Closed Convex Hull of a Function?

Cited in

(8)

• Inexact version of Bregman proximal gradient algorithm
• The NC-proximal average for multiple functions
• A proximal average for nonconvex functions: a proximal stability perspective
• A proximal average for prox-bounded functions
• Proximal averages for minimization of entropy functionals
• The Semiconvex Regularization of Functions
• Dualities for Non-Euclidean Smoothness and Strong Convexity under the Light of Generalized Conjugacy
• Anisotropic proximal gradient

This page was built for publication: The Bregman proximal average

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5081784)