Accelerated dual-averaging primal–dual method for composite convex minimization
From MaRDI portal
Publication:5135253
Abstract: Dual averaging-type methods are widely used in industrial machine learning applications due to their ability to promoting solution structure (e.g., sparsity) efficiently. In this paper, we propose a novel accelerated dual-averaging primal-dual algorithm for minimizing a composite convex function. We also derive a stochastic version of the proposed method which solves empirical risk minimization, and its advantages on handling sparse data are demonstrated both theoretically and empirically.
Recommendations
- Accelerated first-order primal-dual proximal methods for linearly constrained composite convex programming
- A note on the (accelerated) proximal gradient method for composite convex optimization
- A smooth primal-dual optimization framework for nonsmooth composite convex minimization
- A generalized Frank-Wolfe method with ``dual averaging for strongly convex composite optimization
- Fast primal-dual gradient method for strongly convex minimization problems with linear constraints
- Accelerated Dual Averaging Methods for Decentralized Constrained Optimization
- Stochastic primal dual fixed point method for composite optimization
- Efficient primal-dual fixed point algorithms with dynamic stepsize for composite convex optimization problems
- An average curvature accelerated composite gradient method for nonconvex smooth composite optimization problems
- A fast dual proximal gradient algorithm for convex minimization and applications
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 proximal stochastic gradient method with progressive variance reduction
- A survey of algorithms and analysis for adaptive online learning
- An optimal randomized incremental gradient method
- Dual averaging methods for regularized stochastic learning and online optimization
- scientific article; zbMATH DE number 3862940 (Why is no real title available?)
- scientific article; zbMATH DE number 3534286 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Katyusha: the first direct acceleration of stochastic gradient methods
- Primal-dual subgradient methods for convex problems
- Stochastic primal-dual coordinate method for regularized empirical risk minimization
Cited in
(7)- Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems
- Proximal average approximated incremental gradient descent for composite penalty regularized empirical risk minimization
- Dual averaging methods for regularized stochastic learning and online optimization
- Stochastic primal-dual coordinate method for regularized empirical risk minimization
- Accelerated smoothing hard thresholding algorithms for \(\ell_0\) regularized nonsmooth convex regression problem
- Non-ergodic convergence rate of an inertial accelerated primal-dual algorithm for saddle point problems
- Some primal-dual theory for subgradient methods for strongly convex optimization
This page was built for publication: Accelerated dual-averaging primal–dual method for composite convex minimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5135253)
