Stochastic primal dual fixed point method for composite optimization
From MaRDI portal
Abstract: In this paper we propose a stochastic primal dual fixed point method (SPDFP) for solving the sum of two proper lower semi-continuous convex function and one of which is composite. The method is based on the primal dual fixed point method (PDFP) proposed in [7] that does not require subproblem solving. Under some mild condition, the convergence is established based on two sets of assumptions: bounded and unbounded gradients and the convergence rate of the expected error of iterate is of the order O(k^{alpha}) where k is iteration number and alpha in (0, 1]. Finally, numerical examples on graphic Lasso and logistic regressions are given to demonstrate the effectiveness of the proposed algorithm.
Recommendations
- A fully stochastic primal-dual algorithm
- A stochastic variance reduced primal dual fixed point method for linearly constrained separable optimization
- On stochastic primal-dual hybrid gradient approach for compositely regularized minimization
- Efficient primal-dual fixed point algorithms with dynamic stepsize for composite convex optimization problems
- A stochastic variance reduction algorithm with Bregman distances for structured composite problems
Cites work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- A first-order primal-dual algorithm for convex problems with applications to imaging
- A primal–dual fixed point algorithm for convex separable minimization with applications to image restoration
- A proximal stochastic gradient method with progressive variance reduction
- Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
- Dual averaging methods for regularized stochastic learning and online optimization
- Efficient online and batch learning using forward backward splitting
- scientific article; zbMATH DE number 4015993 (Why is no real title available?)
- scientific article; zbMATH DE number 1391397 (Why is no real title available?)
- Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data
- New Proximal Point Algorithms for Convex Minimization
- On the \(O(1/n)\) convergence rate of the Douglas-Rachford alternating direction method
- On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators
- On the global and linear convergence of the generalized alternating direction method of multipliers
- Optimal primal-dual methods for a class of saddle point problems
- Proximity algorithms for image models: denoising
- Signal Recovery by Proximal Forward-Backward Splitting
- Sparse inverse covariance estimation with the graphical lasso
- Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications
Cited in
(22)- The complexity of primal-dual fixed point methods for ridge regression
- Universal method for stochastic composite optimization problems
- A stochastic primal-dual method for a class of nonconvex constrained optimization
- A modified primal-dual method with applications to some sparse recovery problems
- Primal-dual mirror descent method for constraint stochastic optimization problems
- An optimal method for stochastic composite optimization
- On stochastic primal-dual hybrid gradient approach for compositely regularized minimization
- Primal-Dual Stochastic Gradient Method for Convex Programs with Many Functional Constraints
- Accelerated dual-averaging primal–dual method for composite convex minimization
- A first-order stochastic primal-dual algorithm with correction step
- A stochastic variance reduced primal dual fixed point method for linearly constrained separable optimization
- A new randomized primal-dual algorithm for convex optimization with fast last iterate convergence rates
- A dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems
- A stochastic Bregman primal-dual splitting algorithm for composite optimization
- Linearly-convergent FISTA variant for composite optimization with duality
- A stochastic variance reduction algorithm with Bregman distances for structured composite problems
- Accelerated stochastic Peaceman-Rachford method for empirical risk minimization
- Federated primal dual fixed point algorithm
- Optimization constraints and practical implementations of a stochastic primal-dual fixed-point algorithm for blind image deconvolution
- Two modified schemes for the primal dual fixed point method
- An accelerated stochastic primal-dual fixed point approach for image deblurring
- A fully stochastic primal-dual algorithm
This page was built for publication: Stochastic primal dual fixed point method for composite optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q777039)
