ADMM and inexact ALM: the QP case

12/16/2020
by   Stefano Cipolla, et al.
0

Embedding randomization procedures in the Alternating Direction Method of Multipliers (ADMM) has recently attracted an increasing amount of interest as a remedy to the fact that the direct n-block generalization of ADMM is not necessarily convergent (n ≥ 3). Even if, in practice, the introduction of such techniques could mitigate the diverging behaviour of the n-block extension of ADMM, from the theoretical point of view, it can ensure just the convergence in expectation, which may not be a good indicator of its robustness and efficiency. In this work, analysing the strongly convex quadratic programming case, we interpret the n-block Gauss-Seidel sweep performed by ADMM in the context of the inexact Augmented Lagrangian Method. Using the proposed analysis, we are able to outline an alternative technique to those present in literature which, supported from stronger theoretical guarantees, is able to ensure the convergence of the n-block generalization of the ADMM method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2015

Global Convergence of Unmodified 3-Block ADMM for a Class of Convex Minimization Problems

The alternating direction method of multipliers (ADMM) has been successf...
research
02/23/2018

Distributed Optimal Power Flow using ALADIN

The present paper applies the recently proposed Augmented Lagrangian Alt...
research
07/10/2019

Two-block vs. Multi-block ADMM: An empirical evaluation of convergence

Alternating Direction Method of Multipliers (ADMM) has become a widely u...
research
08/04/2020

Faster Stochastic Alternating Direction Method of Multipliers for Nonconvex Optimization

In this paper, we propose a faster stochastic alternating direction meth...
research
07/06/2020

Quantifying the asymptotic linear convergence speed of Anderson Acceleration applied to ADMM

We explain how Anderson Acceleration (AA) speeds up the Alternating Dire...
research
12/22/2021

A Convergent ADMM Framework for Efficient Neural Network Training

As a well-known optimization framework, the Alternating Direction Method...
research
08/10/2023

Learning (With) Distributed Optimization

This paper provides an overview of the historical progression of distrib...

Please sign up or login with your details

Forgot password? Click here to reset