Approaching nonsmooth nonconvex minimization through second-order proximal-gradient dynamical systems
From MaRDI portal
Kurdyka-Łojasiewicz propertylimiting subdifferentialnonsmooth nonconvex optimizationsecond-order dynamical system
Asymptotic properties of solutions to ordinary differential equations (34D05) Nonlinear differential equations in abstract spaces (34G20) Monotone operators and generalizations (47H05) Iterative procedures involving nonlinear operators (47J25) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30)
Abstract: We investigate the asymptotic properties of the trajectories generated by a second-order dynamical system of proximal-gradient type stated in connection with the minimization of the sum of a nonsmooth convex and a (possibly nonconvex) smooth function. The convergence of the generated trajectory to a critical point of the objective is ensured provided a regularization of the objective function satisfies the Kurdyka-L{}ojasiewicz property. We also provide convergence rates for the trajectory formulated in terms of the L{}ojasiewicz exponent.
Recommendations
- Approaching nonsmooth nonconvex optimization problems through first order dynamical systems with hidden acceleration and Hessian driven damping terms
- Fast inertial dynamic algorithm with smoothing method for nonsmooth convex optimization
- A second-order dynamical approach with variable damping to nonconvex smooth minimization
- A forward-backward dynamical approach to the minimization of the sum of a nonsmooth convex with a smooth nonconvex function
- Newton-like dynamics associated to nonconvex optimization problems
Cites work
- A continuous dynamical Newton-like approach to solving monotone inclusions
- A dynamic approach to a proximal-Newton method for monotone inclusions in Hilbert spaces, with complexity \(\mathcal{O}(1/n^2)\)
- A dynamical system associated with the fixed points set of a nonexpansive operator
- A second-order gradient-like dissipative dynamical system with Hessian-driven damping. Application to optimization and mechanics.
- An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions
- An inertial proximal method for maximal monotone operators via discretization of a nonlinear oscillator with damping
- Approaching the solving of constrained variational inequalities via penalty term-based dynamical systems
- Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
- Clarke Subgradients of Stratifiable Functions
- Continuous gradient projection method in Hilbert spaces
- Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
- Convergence of solutions to second-order gradient-like systems with analytic nonlinearities
- Convergence rates for forward-backward dynamical systems associated with strongly monotone inclusions
- Dynamical systems and forward-backward algorithms associated with the sum of a convex subdifferential and a monotone cocoercive operator
- scientific article; zbMATH DE number 48893 (Why is no real title available?)
- scientific article; zbMATH DE number 1487987 (Why is no real title available?)
- scientific article; zbMATH DE number 917233 (Why is no real title available?)
- scientific article; zbMATH DE number 3371284 (Why is no real title available?)
- scientific article; zbMATH DE number 3398324 (Why is no real title available?)
- iPiano: inertial proximal algorithm for nonconvex optimization
- Newton-like dynamics and forward-backward methods for structured monotone inclusions in Hilbert spaces
- On gradients of functions definable in o-minimal structures
- On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
- On the Minimizing Property of a Second Order Dissipative System in Hilbert Spaces
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Proximal Alternating Minimization and Projection Methods for Nonconvex Problems: An Approach Based on the Kurdyka-Łojasiewicz Inequality
- Second order forward-backward dynamical systems for monotone inclusion problems
- The convergence problem for dissipative autonomous systems. Classical methods and recent advances
- 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 Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
- Variational Analysis
- Variational Analysis and Generalized Differentiation I
- Variational Analysis in Sobolev and BV Spaces
- Weak Convergence of a Relaxed and Inertial Hybrid Projection-Proximal Point Algorithm for Maximal Monotone Operators in Hilbert Space
Cited in
(19)- Approaching nonsmooth nonconvex optimization problems through first order dynamical systems with hidden acceleration and Hessian driven damping terms
- Asymptotic analysis of a structure-preserving integrator for damped Hamiltonian systems
- Convergence rates for the heavy-ball continuous dynamics for non-convex optimization, under Polyak-Łojasiewicz condition
- Fast convex optimization via inertial dynamics combining viscous and Hessian-driven damping with time rescaling
- A gradient-type algorithm with backward inertial steps associated to a nonconvex minimization problem
- An extension of the second order dynamical system that models Nesterov's convex gradient method
- Convergence rates for an inertial algorithm of gradient type associated to a smooth non-convex minimization
- Newton-like dynamics associated to nonconvex optimization problems
- Two structure-preserving time discretizations for gradient flows
- A forward-backward dynamical approach for nonsmooth problems with block structure coupled by a smooth function
- A forward-backward dynamical approach to the minimization of the sum of a nonsmooth convex with a smooth nonconvex function
- A new minimizing-movements scheme for curves of maximal slope
- A second-order dynamical approach with variable damping to nonconvex smooth minimization
- Second-Order Guarantees of Stochastic Gradient Descent in Nonconvex Optimization
- Fast optimization via inertial dynamics with closed-loop damping
- A nonmonotone accelerated proximal gradient method with variable stepsize strategy for nonsmooth and nonconvex minimization problems
- Solving convex optimization problems via a second order dynamical system with implicit Hessian damping and Tikhonov regularization
- Regularized Lotka-Volterra dynamical system as continuous proximal-like method in optimization.
- Continuous dynamics related to monotone inclusions and non-smooth optimization problems
This page was built for publication: Approaching nonsmooth nonconvex minimization through second-order proximal-gradient dynamical systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1991713)
