Convergence rates of inertial forward-backward algorithms

DOI10.1137/17M1114739zbMATH Open1387.49047MaRDI QIDQ4609474FDOQ4609474

Authors: Hédy Attouch, Alexandre Cabot 

Publication date: 3 April 2018

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

Recommendations

• Convergence rate of inertial forward-backward algorithm beyond Nesterov's rule
• Convergence rate of inertial proximal algorithms with general extrapolation and proximal coefficients
• Fast convergence of generalized forward-backward algorithms for structured monotone inclusions
• A dynamical approach to an inertial forward-backward algorithm for convex minimization
• Convergence rate of a relaxed inertial proximal algorithm for convex minimization

zbMATH Keywords

structured convex optimizationNesterov methodaccelerated gradient methodFISTAinertial forward-backward algorithmsvanishing dampingproximal-based methods

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Numerical methods based on nonlinear programming (49M37)

Cites Work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Convex analysis and monotone operator theory in Hilbert spaces
• Introductory lectures on convex optimization. A basic course.
• Adaptive restart for accelerated gradient schemes
• Title not available (Why is that?)
• Signal Recovery by Proximal Forward-Backward Splitting
• Accelerated and inexact forward-backward algorithms
• Weak convergence of the sequence of successive approximations for nonexpansive mappings
• Produits infinis de resolvantes
• Title not available (Why is that?)
• On the Convergence of the Proximal Point Algorithm for Convex Minimization
• On the Minimizing Property of a Second Order Dissipative System in Hilbert Spaces
• An inertial proximal method for maximal monotone operators via discretization of a nonlinear oscillator with damping
• Asymptotics for some proximal-like method involving inertia and memory aspects
• A dynamical approach to an inertial forward-backward algorithm for convex minimization
• A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
• Optimized first-order methods for smooth convex minimization
• Some methods of speeding up the convergence of iteration methods
• An inertial forward-backward algorithm for monotone inclusions
• Asymptotic convergence of nonlinear contraction semigroups in Hilbert space
• On the Long Time Behavior of Second Order Differential Equations with Asymptotically Small Dissipation
• On the long time behavior of second order differential equations with asymptotically small dissipation
• On the convergence of the iterates of the ``fast iterative shrinkage/thresholding algorithm
• Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
• Asymptotics for a second-order differential equation with nonautonomous damping and an integrable source term
• Un exemple concernant le comportement asymptotique de la solution du problème \(du/dt+\partial\varphi(\mu)\ni=0\)
• The rate of convergence of Nesterov's accelerated forward-backward method is actually faster than \(1/k^2\)
• Second order forward-backward dynamical systems for monotone inclusion problems
• On damped second-order gradient systems
• Stability of over-relaxations for the forward-backward algorithm, application to FISTA
• Asymptotic stabilization of inertial gradient dynamics with time-dependent viscosity
• The remarkable effectiveness of time-dependent damping terms for second order evolution equations
• Asymptotic for a second-order evolution equation with convex potential and vanishing damping term

Cited In (78)

• Convergence Theorems and Convergence Rates for the General Inertial Krasnosel’skiǐ–Mann Algorithm
• Finite-time stabilization of continuous inertial dynamics combining dry friction with Hessian-driven damping
• Fast Proximal Methods via Time Scaling of Damped Inertial Dynamics
• Fast convergence of dynamical ADMM via time scaling of damped inertial dynamics
• A proximal subgradient algorithm with extrapolation for structured nonconvex nonsmooth problems
• Improved convergence rates and trajectory convergence for primal-dual dynamical systems with vanishing damping
• Asymptotics for some proximal-like method involving inertia and memory aspects
• Inertial forward-backward algorithms with perturbations: application to Tikhonov regularization
• Fast optimization via inertial dynamics with closed-loop damping
• Convergence rate of inertial forward-backward algorithm beyond Nesterov's rule
• Convergence of inertial dynamics and proximal algorithms governed by maximally monotone operators
• On the strong convergence of a projection-based algorithm in Hilbert spaces
• Accelerated dynamics with dry friction via time scaling and averaging of doubly nonlinear evolution equations
• An explicit algorithm for solving monotone variational inequalities
• Accelerated methods with fastly vanishing subgradients for structured non-smooth minimization
• Convergence rates for the heavy-ball continuous dynamics for non-convex optimization, under Polyak-Łojasiewicz condition
• Convergence of iterates for first-order optimization algorithms with inertia and Hessian driven damping
• Newton-like inertial dynamics and proximal algorithms governed by maximally monotone operators
• Continuous Newton-like inertial dynamics for monotone inclusions
• First-order inertial algorithms involving dry friction damping
• Inertial algorithms for a system of equilibrium problems and fixed point problems
• Convergence rates of an inertial gradient descent algorithm under growth and flatness conditions
• Convergence rate of a relaxed inertial proximal algorithm for convex minimization
• Convergence of a relaxed inertial proximal algorithm for maximally monotone operators
• Convergence of a relaxed inertial forward-backward algorithm for structured monotone inclusions
• From the ravine method to the Nesterov method and vice versa: a dynamical system perspective
• Convergence rates of the heavy-ball method under the Łojasiewicz property
• The rate of convergence of optimization algorithms obtained via discretizations of heavy ball dynamical systems for convex optimization problems
• Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
• The rate of convergence of Nesterov's accelerated forward-backward method is actually faster than \(1/k^2\)
• New analysis of linear convergence of gradient-type methods via unifying error bound conditions
• A dynamical approach to an inertial forward-backward algorithm for convex minimization
• Fast convex optimization via inertial dynamics combining viscous and Hessian-driven damping with time rescaling
• First-order optimization algorithms via inertial systems with Hessian driven damping
• First-order frameworks for continuous Newton-like dynamics governed by maximally monotone operators
• From differential equation solvers to accelerated first-order methods for convex optimization
• Convergence results of a new monotone inertial forward-backward splitting algorithm under the local Hölder error bound condition
• iPiasco: inertial proximal algorithm for strongly convex optimization
• Behavior of accelerated gradient methods near critical points of nonconvex functions
• Understanding the acceleration phenomenon via high-resolution differential equations
• Double inertial parameters forward-backward splitting method: Applications to compressed sensing, image processing, and SCAD penalty problems
• Convergence of inertial dynamics driven by sums of potential and nonpotential operators with implicit Newton-like damping
• Weak and strong convergence of inertial algorithms for solving split common fixed point problems
• Fast convex optimization via a third-order in time evolution equation
• Tikhonov regularization of a perturbed heavy ball system with vanishing damping
• Some modified fast iterative shrinkage thresholding algorithms with a new adaptive non-monotone stepsize strategy for nonsmooth and convex minimization problems
• Finite convergence of proximal-gradient inertial algorithms combining dry friction with Hessian-driven damping
• Fast proximal algorithms for nonsmooth convex optimization
• Improving ``fast iterative shrinkage-thresholding algorithm: faster, smarter, and greedier
• On FISTA with a relative error rule
• Stability of over-relaxations for the forward-backward algorithm, application to FISTA
• Rate of convergence of the Nesterov accelerated gradient method in the subcritical case α ≤ 3
• Title not available (Why is that?)
• Convergence rate of inertial proximal algorithms with general extrapolation and proximal coefficients
• Applying FISTA to optimization problems (with or) without minimizers
• Convergence rates of damped inertial dynamics under geometric conditions and perturbations
• Inertial, corrected, primal-dual proximal splitting
• Complexity analysis based on tuning the viscosity parameter of the Su-Boyd-Candès inertial gradient dynamics
• A class of modified accelerated proximal gradient methods for nonsmooth and nonconvex minimization problems
• First order inertial optimization algorithms with threshold effects associated with dry friction
• Modified inertial projection and contraction algorithms with non-monotonic step sizes for solving variational inequalities and their applications
• An accelerated forward-backward-half forward splitting algorithm for monotone inclusion with applications to image restoration
• A novel method for hierarchical variational inequality with split common fixed point constraint
• Fast augmented Lagrangian method in the convex regime with convergence guarantees for the iterates
• A nonmonotone accelerated proximal gradient method with variable stepsize strategy for nonsmooth and nonconvex minimization problems
• A new optimization approach to solving split equality problems in Hilbert spaces
• The second-order differential equation method for solving the variational inequality problem
• Inertial proximal point algorithms for solving a class of split feasibility problems
• Fast convex optimization via a third-order in time evolution equation: TOGES-V an improved version of TOGES*
• Alternated inertial fixed point algorithms
• Parameter-free FISTA by adaptive restart and backtracking
• Nonlinear forward-backward splitting with momentum correction
• Three shrinking projection methods with multiple inertial effects for solving a class of split feasibility problems
• Two inertial hybrid projection algorithms for solving a class of split common solution problems
• A novel inertial proximal contraction-type algorithm with self-adaptive step size for solving monotone variational inclusion problems
• Fast convergence of the primal-dual dynamical system and corresponding algorithms for a nonsmooth bilinearly coupled saddle point problem
• An improved parameterized fast iterative shrinkage-thresholding algorithm with adaptive step size and its applications
• On a new simple algorithm to compute the resolvents

This page was built for publication: Convergence rates of inertial forward-backward algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4609474)