Convergence of non-smooth descent methods using the Kurdyka-Łojasiewicz inequality
From MaRDI portal
Publication:2251554
DOI10.1007/s10957-013-0391-8zbMath1298.90079MaRDI QIDQ2251554
Publication date: 14 July 2014
Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10957-013-0391-8
Kurdyka-Łojasiewicz inequality; lower-\(C^1\); non-smooth non-convex optimization; strict model; subgradient-oriented descent method; upper-\(C^1\)
90C26: Nonconvex programming, global optimization
Related Items
Line Search Algorithms for Locally Lipschitz Functions on Riemannian Manifolds, Unifying Abstract Inexact Convergence Theorems and Block Coordinate Variable Metric iPiano, Convergence of alternating direction method for minimizing sum of two nonconvex functions with linear constraints, A Nonsmooth Trust-Region Method for Locally Lipschitz Functions with Application to Optimization Problems Constrained by Variational Inequalities, The Boosted Difference of Convex Functions Algorithm for Nonsmooth Functions, Worst‐case stability and performance with mixed parametric and dynamic uncertainties, A Bregman Forward-Backward Linesearch Algorithm for Nonconvex Composite Optimization: Superlinear Convergence to Nonisolated Local Minima, Extrapolated Proximal Subgradient Algorithms for Nonconvex and Nonsmooth Fractional Programs, A Unified Analysis of Descent Sequences in Weakly Convex Optimization, Including Convergence Rates for Bundle Methods, A gradient sampling algorithm for stratified maps with applications to topological data analysis, Nonsmooth bundle trust-region algorithm with applications to robust stability, Semicoercive variational inequalities: from existence to numerical solution of nonmonotone contact problems, Branch and bound algorithm with applications to robust stability, Local convergence of the heavy-ball method and iPiano for non-convex optimization, Proximal algorithms in statistics and machine learning, A block coordinate variable metric linesearch based proximal gradient method, A bundle method for nonsmooth DC programming with application to chance-constrained problems, Perturbation techniques for convergence analysis of proximal gradient method and other first-order algorithms via variational analysis, A survey on some recent developments of alternating direction method of multipliers, Faster subgradient methods for functions with Hölderian growth, Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates, Non-smooth non-convex Bregman minimization: unification and new algorithms, An abstract convergence framework with application to inertial inexact forward-backward methods, Robust eigenstructure clustering by non-smooth optimisation, Majorization-Minimization Procedures and Convergence of SQP Methods for Semi-Algebraic and Tame Programs, Convergence Results for Projected Line-Search Methods on Varieties of Low-Rank Matrices Via Łojasiewicz Inequality
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On local convergence of the method of alternating projections
- Design of a flight control architecture using a non-convex bundle method
- Cutting plane oracles to minimize non-smooth non-convex functions
- On Nesterov's nonsmooth Chebyshev-Rosenbrock functions
- Nonsmooth optimization for multiband frequency domain control design
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- On the projected subgradient method for nonsmooth convex optimization in a Hilbert space
- Optimization. Algorithms and consistent approximations
- Approximate convexity and submonotonicity.
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Computational and analytical mathematics. In Honor of Jonathan Borwein's 60th birthday. Selected papers based on the presentations at the workshop, also known as JonFest, Simon Fraser University, BC, Canada, May 16--20, 2011
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Clarke Subgradients of Stratifiable Functions
- Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
- A Trust Region Spectral Bundle Method for Nonconvex Eigenvalue Optimization
- Mixed $H_2/H_\infty$ Control via Nonsmooth Optimization
- Submonotone Subdifferentials of Lipschitz Functions
- An Infeasible Bundle Method for Nonsmooth Convex Constrained Optimization without a Penalty Function or a Filter
- The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Convergence of the Iterates of Descent Methods for Analytic Cost Functions
