Proximal-proximal-gradient method
From MaRDI portal
Abstract: In this paper, we present the proximal-proximal-gradient method (PPG), a novel optimization method that is simple to implement and simple to parallelize. PPG generalizes the proximal-gradient method and ADMM and is applicable to minimization problems written as a sum of many differentiable and many non-differentiable convex functions. The non-differentiable functions can be coupled. We furthermore present a related stochastic variation, which we call stochastic PPG (S-PPG). S-PPG can be interpreted as a generalization of Finito and MISO over to the sum of many coupled non-differentiable convex functions. We present many applications that can benefit from PPG and S-PPG and prove convergence for both methods. A key strength of PPG and S-PPG is, compared to existing methods, its ability to directly handle a large sum of non-differentiable non-separable functions with a constant stepsize independent of the number of functions. Such non-diminishing stepsizes allows them to be fast.
Recommendations
- Common fixed points of an infinite family of nonexpansive mappings in uniformly convex metric spaces
- Incremental proximal methods for large scale convex optimization
- scientific article; zbMATH DE number 7404502
- Gradient methods for minimizing composite functions
- A proximal stochastic gradient method with progressive variance reduction
Cited in
(15)- Continuous regularized proximal minimization method
- Proximal algorithms in statistics and machine learning
- Solving a class of nonsmooth resource allocation problems with directed graphs through distributed Lipschitz continuous multi-proximal algorithms
- Sub-linear convergence of a stochastic proximal iteration method in Hilbert space
- Common fixed points of an infinite family of nonexpansive mappings in uniformly convex metric spaces
- An inexact Riemannian proximal gradient method
- Distributed Proximal Gradient Algorithm for Partially Asynchronous Computer Clusters
- Proximal gradient method with automatic selection of the parameter by automatic differentiation
- A proximal regularization of the steepest descent method
- Sublinear convergence of a tamed stochastic gradient descent method in Hilbert space
- Primal-Dual Stochastic Gradient Method for Convex Programs with Many Functional Constraints
- Proximal Methods in Vector Optimization
- A general framework for inexact splitting algorithms with relative errors and applications to Chambolle-Pock and Davis-Yin methods
- Proximal linear maps
- Parametric proximal-point methods
This page was built for publication: Proximal-proximal-gradient method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5127589)
