Global convergence of model function based Bregman proximal minimization algorithms
From MaRDI portal
Publication:2154449
Abstract: Lipschitz continuity of the gradient mapping of a continuously differentiable function plays a crucial role in designing various optimization algorithms. However, many functions arising in practical applications such as low rank matrix factorization or deep neural network problems do not have a Lipschitz continuous gradient. This led to the development of a generalized notion known as the -smad property, which is based on generalized proximity measures called Bregman distances. However, the -smad property cannot handle nonsmooth functions, for example, simple nonsmooth functions like and also many practical composite problems are out of scope. We fix this issue by proposing the MAP property, which generalizes the -smad property and is also valid for a large class of nonconvex nonsmooth composite problems. Based on the proposed MAP property, we propose a globally convergent algorithm called Model BPG, that unifies several existing algorithms. The convergence analysis is based on a new Lyapunov function. We also numerically illustrate the superior performance of Model BPG on standard phase retrieval problems, robust phase retrieval problems, and Poisson linear inverse problems, when compared to a state of the art optimization method that is valid for generic nonconvex nonsmooth optimization problems.
Recommendations
- A Bregman stochastic method for nonconvex nonsmooth problem beyond global Lipschitz gradient continuity
- Non-smooth non-convex Bregman minimization: unification and new algorithms
- Convergence properties of monotone and nonmonotone proximal gradient methods revisited
- First order methods beyond convexity and Lipschitz gradient continuity with applications to quadratic inverse problems
- A globally convergent proximal Newton-type method in nonsmooth convex optimization
Cites work
- A descent lemma beyond Lipschitz gradient continuity: first-order methods revisited and applications
- A proximal method for composite minimization
- An iterative row-action method for interval convex programming
- Analysis of the Recovery of Edges in Images and Signals by Minimizing Nonconvex Regularized Least-Squares
- Bregman Monotone Optimization Algorithms
- Bregman proximal gradient algorithms for deep matrix factorization
- Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
- Clarke Subgradients of Stratifiable Functions
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Convex-concave backtracking for inertial Bregman proximal gradient algorithms in nonconvex optimization
- Efficiency of minimizing compositions of convex functions and smooth maps
- Error bounds, quadratic growth, and linear convergence of proximal methods
- ESSENTIAL SMOOTHNESS, ESSENTIAL STRICT CONVEXITY, AND LEGENDRE FUNCTIONS IN BANACH SPACES
- First order methods beyond convexity and Lipschitz gradient continuity with applications to quadratic inverse problems
- First-order optimization algorithms via inertial systems with Hessian driven damping
- Geometric categories and o-minimal structures
- scientific article; zbMATH DE number 1266748 (Why is no real title available?)
- scientific article; zbMATH DE number 1046019 (Why is no real title available?)
- scientific article; zbMATH DE number 3296905 (Why is no real title available?)
- Image deblurring with Poisson data: from cells to galaxies
- Introductory lectures on convex optimization. A basic course.
- iPiano: inertial proximal algorithm for nonconvex optimization
- Mirror descent and nonlinear projected subgradient methods for convex optimization.
- Modified Gauss–Newton scheme with worst case guarantees for global performance
- New fractional error bounds for polynomial systems with applications to Hölderian stability in optimization and spectral theory of tensors
- Non-smooth non-convex Bregman minimization: unification and new algorithms
- Nonsmooth optimization using Taylor-like models: error bounds, convergence, and termination criteria
- Novel proximal gradient methods for nonnegative matrix factorization with sparsity constraints
- On gradients of functions definable in o-minimal structures
- On iteratively reweighted algorithms for nonsmooth nonconvex optimization in computer vision
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- Phase retrieval via Wirtinger flow: theory and algorithms
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Relatively smooth convex optimization by first-order methods, and applications
- Solving Systems of Random Quadratic Equations via Truncated Amplitude Flow
- Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
- THE HEAVY BALL WITH FRICTION METHOD, I. THE CONTINUOUS DYNAMICAL SYSTEM: GLOBAL EXPLORATION OF THE LOCAL MINIMA OF A REAL-VALUED FUNCTION BY ASYMPTOTIC ANALYSIS OF A DISSIPATIVE DYNAMICAL SYSTEM
- The importance of better models in stochastic optimization
- The value function approach to convergence analysis in composite optimization
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Unifying abstract inexact convergence theorems and block coordinate variable metric iPiano
- Variational Analysis
- Variational analysis and applications
Cited in
(3)
This page was built for publication: Global convergence of model function based Bregman proximal minimization algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2154449)
