Bregman Alternating Direction Method of Multipliers

06/13/2013
by   Huahua Wang, et al.
0

The mirror descent algorithm (MDA) generalizes gradient descent by using a Bregman divergence to replace squared Euclidean distance. In this paper, we similarly generalize the alternating direction method of multipliers (ADMM) to Bregman ADMM (BADMM), which allows the choice of different Bregman divergences to exploit the structure of problems. BADMM provides a unified framework for ADMM and its variants, including generalized ADMM, inexact ADMM and Bethe ADMM. We establish the global convergence and the O(1/T) iteration complexity for BADMM. In some cases, BADMM can be faster than ADMM by a factor of O(n/(n)). In solving the linear program of mass transportation problem, BADMM leads to massive parallelism and can easily run on GPU. BADMM is several times faster than highly optimized commercial software Gurobi.

READ FULL TEXT

page 1

page 2

page 3

page 4

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
01/27/2019

Large-Scale Classification using Multinomial Regression and ADMM

We present a novel method for learning the weights in multinomial logist...
research
02/13/2022

Quasistatic cohesive fracture with an alternating direction method of multipliers

A method for quasistatic cohesive fracture is introduced that uses an al...
research
09/26/2013

Bethe-ADMM for Tree Decomposition based Parallel MAP Inference

We consider the problem of maximum a posteriori (MAP) inference in discr...
research
12/16/2013

Adaptive Stochastic Alternating Direction Method of Multipliers

The Alternating Direction Method of Multipliers (ADMM) has been studied ...
research
03/08/2016

Testing fine-grained parallelism for the ADMM on a factor-graph

There is an ongoing effort to develop tools that apply distributed compu...
research
07/07/2019

Fast and Provable ADMM for Learning with Generative Priors

In this work, we propose a (linearized) Alternating Direction Method-of-...

Please sign up or login with your details

Forgot password? Click here to reset