On the Complexity of a Practical Primal-Dual Coordinate Method

01/19/2022
by   Ahmet Alacaoglu, et al.
0

We prove complexity bounds for the primal-dual algorithm with random extrapolation and coordinate descent (PURE-CD), which has been shown to obtain good practical performance for solving convex-concave min-max problems with bilinear coupling. Our complexity bounds either match or improve the best-known results in the literature for both dense and sparse (strongly)-convex-(strongly)-concave problems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/10/2022

Accelerated Primal-Dual Methods for Convex-Strongly-Concave Saddle Point Problems

In this work, we aim to investigate Primal-Dual (PD) methods for convex-...
research
07/13/2020

Random extrapolation for primal-dual coordinate descent

We introduce a randomly extrapolated primal-dual coordinate descent meth...
research
11/02/2021

Coordinate Linear Variance Reduction for Generalized Linear Programming

We study a class of generalized linear programs (GLP) in a large-scale s...
research
11/23/2015

Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems

We consider convex-concave saddle point problems with a separable struct...
research
09/17/2020

Coordinate Methods for Matrix Games

We develop primal-dual coordinate methods for solving bilinear saddle-po...
research
12/22/2022

Distributed Random Block-Coordinate descent methods for ill-posed composite convex optimisation problems

We develop a novel randomised block coordinate descent primal-dual algor...
research
12/15/2022

Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems

We leverage path differentiability and a recent result on nonsmooth impl...

Please sign up or login with your details

Forgot password? Click here to reset