Entropy-Like Proximal Methods in Convex Programming
Mathematics of Operations ResearchPublished 1 November 1994
Alfredo N. Iusem, B. F. Svaiter, Marc Teboulle
Citations154
SJR quartileQ1
SJR score1.35
SNIP1.90
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An extension of the proximal method for convex programming, where the quadratic regularization kernel is substituted by a class of convex statistical distances, called φ- divergences, is studied and a convergence analysis of the resulting entropy-like proximal algorithm is presented.
Abstract
We study an extension of the proximal method for convex programming, where the quadratic regularization kernel is substituted by a class of convex statistical distances, called φ-divergences, which are typically entropy-like in form. After establishing several basic properties of these quasi-distances, we present a convergence analysis of the resulting entropy-like proximal algorithm. Applying this algorithm to the dual of a convex program, we recover a wide class of nonquadratic multiplier methods and prove their convergence.
Keywords
Computer ScienceMathematicsEngineering
Society for Industrial and Applied Mathematics eBooksOptimization and Nonsmooth Analysis
10,418 Citations1990Frank H. Clarke
SIAM Journal on Control and OptimizationMonotone Operators and the Proximal Point Algorithm
3,620 Citations1976R. T. Rockafellar
USSR Computational Mathematics and Mathematical PhysicsThe relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming
2,659 Citations1967L.M. Bregman
This method can be regarded as a generalization of the methods discussed in [1–4] and applied to the approximate solution of problems in linear and convex programming.
Bulletin de la Société mathématique de FranceProximité et dualité dans un espace hilbertien
1,386 Citations1965Jean Jacques Moreau
Mathematics of Operations ResearchAugmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming
1,209 Citations1976R. T. Rockafellar
The theory of the proximal point algorithm for maximal monotone operators is applied to three algorithms for solving convex programs, one of which has not previously been formulated and is shown to have much the same convergence properties, but with some potential advantages.
Mathematics of ComputationAugmented Lagrangian and Operator-Splitting Methods in Nonlinear Mechanics.
1,003 Citations1992J. Tinsley Oden, Roland Glowinski +1 more
SIAM Journal on OptimizationConvergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions
433 Citations1993Gong Chen, Marc Teboulle
An alternative convergence proof of a proximal-like minimization algorithm using Bregman functions, recently proposed by Censor and Zenios, is presented and allows the establishment of a global convergence rate of the algorithm expressed in terms of function values.
Mathematics of Operations ResearchNonlinear Proximal Point Algorithms Using Bregman Functions, with Applications to Convex Programming
326 Citations1993Jonathan Eckstein
Applying this generalization of the proximal point algorithm to convex programming, one obtains the D-function proximal minimization algorithm of Censor and Zenios, and a wide variety of new multiplier methods.
Journal of Optimization Theory and ApplicationsProximal minimization algorithm withD-functions
272 Citations1992Yair Censor, Stavros A. Zenios
This paper replaces quadratic additive terms in the objectives of the subproblems with more general D-functions which resemble (but are not strictly) distance functions which, when used in the proximal minimization algorithm, preserve its overall convergence.
Mathematical ProgrammingModified barrier functions (theory and methods)
254 Citations1992Roman A. Polyak
The excellent MBF properties allow us to discover that for any nondegenerate constrained optimization problem, there exists a “hot” start, from which the NMBM has a better rate of convergence, a better complexity bound, and is more stable than the interior point methods, which are based on the classical barrier functions.
Mathematics of Operations ResearchEntropic Proximal Mappings with Applications to Nonlinear Programming
243 Citations1992Marc Teboulle
A family of new transforms based on imitating the proximal mapping of Moreau and the associated Moreau-Yosida proximal approximation of a function are introduced, providing a fairly general framework for constructing approximation and smoothing schemes for optimization problems.
IEEE Transactions on Automatic ControlOptimal short-term scheduling of large-scale power systems
230 Citations1983Dimitri P. Bertsekas, Gerhard Lauer +2 more
Mathematical ProgrammingOn the convergence of the exponential multiplier method for convex programming
175 Citations1993Paul Tseng, Dimitri P. Bertsekas
This paper analyzes the exponential method of multipliers for convex constrained minimization problems, which operates like the usual Augmented Lagrangian method, except that it uses an exponential penalty function in place of the usual quadratic.
Cybernetics and Systems AnalysisOn the method of generalized stochastic gradients and quasi-F�jer sequences
112 Citations1972Yu. M. Ermol’ev
Journal of Optimization Theory and ApplicationsA relaxed version of Bregman's method for convex programming
102 Citations1986A.R. De Pierro, A. N. Iusem
It is shown that the new relaxation procedure generalizes the usual concept of relaxation and preserves the convergence properties of Bregman's algorithm for a suitable choice of the relaxation parameters.
Linear Algebra and its ApplicationsMultiplicative iterative algorithms for convex programming
99 Citations1990P. P. B. Eggermont
Study of multiplicative iterative algorithms for the minimization of a differentiable, convex function defined on the positive orthant of R N and the convergence is nearly monotone in the sense of Kullback-Leibler divergence.
SIAM Journal on Control and OptimizationSmooth Optimization Methods for Minimax Problems
74 Citations1988Roman A. Polyak
The classical discrete minimax problem is considered and it was found that the classical Lagrangian of the equivalent problem has a number of important properties both in primal and dual spaces in convex as well as in nonconvex cases.
Journal of Mathematical Analysis and ApplicationsCertainty equivalents and information measures: Duality and extremal principles
38 Citations1991Aharon Ben‐Tal, Adi Ben-Israel +1 more
Journal of Approximation TheoryTowards minimal assumptions for the infimal convolution regularization
37 Citations1991M. L. Bougeard, Jean‐Paul Penot +1 more
Spectral Estimation Via Convex Programming
14 Citations1992Aharon Ben‐Tal, Jonathan M. Borwein +1 more
This paper presents a treatment of constrained spline interpolation and spectral estimation of a convex objective function over an infinite-dimensional convex cone subject to a finite number of equality (or inequality) constraints.