iPiano: inertial proximal algorithm for nonconvex optimization
From MaRDI portal
IPiano: inertial proximal algorithm for nonconvex optimization
heavy-ball methodinertial forward-backward splittingKurdyka-Łojasiewicz inequalitynonconvex optimizationproof of convergence
Numerical optimization and variational techniques (65K10) Pattern recognition, speech recognition (68T10) Large-scale problems in mathematical programming (90C06) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Methods of quasi-Newton type (90C53) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)
Abstract: In this paper we study an algorithm for solving a minimization problem composed of a differentiable (possibly non-convex) and a convex (possibly non-differentiable) function. The algorithm iPiano combines forward-backward splitting with an inertial force. It can be seen as a non-smooth split version of the Heavy-ball method from Polyak. A rigorous analysis of the algorithm for the proposed class of problems yields global convergence of the function values and the arguments. This makes the algorithm robust for usage on non-convex problems. The convergence result is obtained based on the KL inequality. This is a very weak restriction, which was used to prove convergence for several other gradient methods. First, an abstract convergence theorem for a generic algorithm is proved, and, then iPiano is shown to satisfy the requirements of this theorem. Furthermore, a convergence rate is established for the general problem class. We demonstrate iPiano on computer vision problems: image denoising with learned priors and diffusion based image compression.
Recommendations
- iPiasco: inertial proximal algorithm for strongly convex optimization
- Inertial proximal alternating linearized minimization (iPALM) for nonconvex and nonsmooth problems
- An inertial proximal alternating direction method of multipliers for nonconvex optimization
- Inertial proximal alternating minimization for nonconvex and nonsmooth problems
- Nonconvex optimization with inertial proximal stochastic variance reduction gradient
- General inertial proximal gradient method for a class of nonconvex nonsmooth optimization problems
- New inertial proximal gradient methods for unconstrained convex optimization problems
- Inertial proximal gradient methods with Bregman regularization for a class of nonconvex optimization problems
- Inertial proximal point regularization algorithm for unconstrained vector convex optimization problems
- Inertial alternating direction method of multipliers for non-convex non-smooth optimization
Cited in
(only showing first 100 items - show all)- Variational methods for normal integration
- Local convergence of the heavy-ball method and iPiano for non-convex optimization
- Approaching nonsmooth nonconvex optimization problems through first order dynamical systems with hidden acceleration and Hessian driven damping terms
- Global convergence of proximal iteratively reweighted algorithm
- The Shannon total variation
- Inertial projection and contraction algorithms for variational inequalities
- Speckle reduction with trained nonlinear diffusion filtering
- Optimisation of classic photometric stereo by non-convex variational minimisation
- Inertial hybrid splitting methods for operator inclusion problems
- Acceleration of the imaginary time method for spectrally computing the stationary states of Gross-Pitaevskii equations
- On the proximal gradient algorithm with alternated inertia
- Proximal primal-dual best approximation algorithm with memory
- Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
- A block coordinate variable metric linesearch based proximal gradient method
- An efficient variational method for restoring images with combined additive and multiplicative noise
- Whiteness constraints in a unified variational framework for image restoration
- A logarithmic image prior for blind deconvolution
- Approximate versions of proximal iteratively reweighted algorithms including an extended IP-ICMM for signal and image processing problems
- A general truncated regularization framework for contrast-preserving variational signal and image restoration: motivation and implementation
- An inertial subgradient-type method for solving single-valued variational inequalities and fixed point problems
- Approaching nonsmooth nonconvex minimization through second-order proximal-gradient dynamical systems
- Inertial alternating generalized forward-backward splitting for image colorization
- On the discontinuity of images recovered by noncovex nonsmooth regularized isotropic models with box constraints
- Linear convergence of inexact descent method and inexact proximal gradient algorithms for lower-order regularization problems
- Inertial proximal gradient methods with Bregman regularization for a class of nonconvex optimization problems
- Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
- A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization
- Inertial iterative algorithms for common solution of variational inequality and system of variational inequalities problems
- An accelerated smoothing gradient method for nonconvex nonsmooth minimization in image processing
- An inexact proximal gradient algorithm with extrapolation for a class of nonconvex nonsmooth optimization problems
- An inertial proximal partially symmetric ADMM-based algorithm for linearly constrained multi-block nonconvex optimization problems with applications
- On the geometric analysis of a quartic-quadratic optimization problem under a spherical constraint
- Two-step inertial Bregman alternating minimization algorithm for nonconvex and nonsmooth problems
- An adaptive Polyak heavy-ball method
- The proximity operator of the log-sum penalty
- Extrapolated smoothing descent algorithm for constrained nonconvex and nonsmooth composite problems
- Generalized fractional algebraic linear system solvers
- Inertial projection and contraction algorithms with larger step sizes for solving quasimonotone variational inequalities
- Convergence results of a new monotone inertial forward-backward splitting algorithm under the local Hölder error bound condition
- Block-coordinate and incremental aggregated proximal gradient methods for nonsmooth nonconvex problems
- Convergence of inexact quasisubgradient methods with extrapolation
- Malitsky-Tam forward-reflected-backward splitting method for nonconvex minimization problems
- Field of experts regularized nonlocal low rank matrix approximation for image denoising
- An inertial Bregman generalized alternating direction method of multipliers for nonconvex optimization
- Self-adaptive inertial subgradient extragradient scheme for pseudomonotone variational inequality problem
- A fast proximal iteratively reweighted nuclear norm algorithm for nonconvex low-rank matrix minimization problems
- Global convergence of model function based Bregman proximal minimization algorithms
- iPiano
- New acceleration factors of the Krasnosel'skiĭ-Mann iteration
- Separating variables to accelerate non-convex regularized optimization
- Bregman Itoh-Abe methods for sparse optimisation
- Ultrasound image restoration based on a learned dictionary and a higher-order MRF
- Convergence rates for an inertial algorithm of gradient type associated to a smooth non-convex minimization
- An inertial algorithm for DC programming
- A Gauss-Seidel type inertial proximal alternating linearized minimization for a class of nonconvex optimization problems
- A new proximal iterative hard thresholding method with extrapolation for \(\ell _0\) minimization
- Block-proximal methods with spatially adapted acceleration
- A general double-proximal gradient algorithm for d.c. programming
- Minimization of non-smooth, non-convex functionals by iterative thresholding
- Splitting methods with variable metric for Kurdyka-Łojasiewicz functions and general convergence rates
- On damped second-order gradient systems
- Forward-backward quasi-Newton methods for nonsmooth optimization problems
- A multi-parameter regularization model for deblurring images corrupted by impulsive noise
- Inertial proximal alternating minimization for nonconvex and nonsmooth problems
- Nonconvex mixed TV/Cahn-Hilliard functional for super-resolution/segmentation of 3D trabecular bone images
- General inertial proximal gradient method for a class of nonconvex nonsmooth optimization problems
- Iteratively reweighted \(\ell _1\) algorithms with extrapolation
- Non-smooth non-convex Bregman minimization: unification and new algorithms
- Generalized forward-backward splitting with penalization for monotone inclusion problems
- An inertial forward-backward-forward primal-dual splitting algorithm for solving monotone inclusion problems
- New convergence results for the inexact variable metric forward-backward method
- A proximal quasi-Newton method based on memoryless modified symmetric rank-one formula
- An abstract convergence framework with application to inertial inexact forward-backward methods
- A smoothing proximal gradient algorithm with extrapolation for the relaxation of \({\ell_0}\) regularization problem
- Pseudo-inverses of difference matrices and their application to sparse signal approximation
- A variable metric forward-backward method with extrapolation
- The extragradient algorithm with inertial effects for solving the variational inequality
- An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions
- Inertial Douglas-Rachford splitting for monotone inclusion problems
- Poisson Noise Reduction with Higher-Order Natural Image Prior Model
- Inertial proximal alternating linearized minimization (iPALM) for nonconvex and nonsmooth problems
- Bilevel optimization with nonsmooth lower level problems
- Techniques for gradient-based bilevel optimization with non-smooth lower level problems
- An accelerated subgradient extragradient algorithm for strongly pseudomonotone variational inequality problems
- A general inertial proximal point algorithm for mixed variational inequality problem
- Inertial proximal ADMM for linearly constrained separable convex optimization
- Limiting aspects of nonconvex \({TV}^{\phi}\) models
- An inertial Tseng's type proximal algorithm for nonsmooth and nonconvex optimization problems
- A forward-backward dynamical approach to the minimization of the sum of a nonsmooth convex with a smooth nonconvex function
- Efficient learning with a family of nonconvex regularizers by redistributing nonconvexity
- Forward-backward envelope for the sum of two nonconvex functions: further properties and nonmonotone linesearch algorithms
- A Symmetric Alternating Direction Method of Multipliers for Separable Nonconvex Minimization Problems
- Geodesic PCA versus Log-PCA of Histograms in the Wasserstein Space
- Unifying abstract inexact convergence theorems and block coordinate variable metric iPiano
- A Fokker-Planck based approach to control jump processes
- Acceleration and global convergence of a first-order primal-dual method for nonconvex problems
- Blind image fusion for hyperspectral imaging with the directional total variation
- On the Edge Recovery Property of Noncovex Nonsmooth Regularization in Image Restoration
- Inertial variable metric techniques for the inexact forward-backward algorithm
- A New Optimization Approach to Sparse Reconstruction of Log-Conductivity in Acousto-Electric Tomography
This page was built for publication: iPiano: inertial proximal algorithm for nonconvex optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2876847)
