Results 21 to 30 of about 404,975 (273)
Distributed Alternating Direction Method of Multipliers [PDF]
2012 IEEE 51st IEEE Conference on Decision and Control (CDC), 2012 We consider a network of agents that are cooperatively solving a global unconstrained optimization problem, where the objective function is the sum of privately known local objective functions of the agents. Recent literature on distributed optimization methods for solving this problem focused on subgradient based methods, which typically converge at ...
Wei, Ermin, Ozdaglar, Asuman E.
openaire +3 more sources
Alternating direction method of multipliers for penalized zero-variance discriminant analysis [PDF]
, 2015 We consider the task of classification in the high dimensional setting where the number of features of the given data is significantly greater than the number of observations.
Ames, Brendan +2 more
core +3 more sources
Distributed Model Predictive Consensus via the Alternating Direction Method of Multipliers [PDF]
, 2012 We propose a distributed optimization method for solving a distributed model predictive consensus problem. The goal is to design a distributed controller for a network of dynamical systems to optimize a coupled objective function while respecting state ...
Lygeros, John, Summers, Tyler H.
core +1 more source
Alternating Direction Method of Multipliers for Quantization
CoRR, 2020 Quantization of the parameters of machine learning models, such as deep neural networks, requires solving constrained optimization problems, where the constraint set is formed by the Cartesian product of many simple discrete sets. For such optimization problems, we study the performance of the Alternating Direction Method of Multipliers for ...
Tianjian Huang +4 more
openaire +3 more sources
A distributed parallel optimization algorithm via alternating direction method of multipliers
IET Control Theory & Applications, 2023 Alternating direction method of multipliers (ADMM) has been widely used for solving the distributed optimisation problems. This paper proposes a novel distributed ADMM algorithm to solve the distributed optimisation problems consisting of convex cost ...
Ziye Liu +3 more
doaj +1 more source
Mathematics, 2023 We adopt the alternating direction search pattern method to solve the equality and inequality constrained nonlinear optimization problems. Firstly, a new augmented Lagrangian function with a nonlinear complementarity function is proposed to transform the
Aifen Feng +3 more
doaj +1 more source
Blind Ptychographic Phase Retrieval via Convergent Alternating Direction Method of Multipliers [PDF]
, 2018 Ptychography has risen as a reference X-ray imaging technique: it achieves resolutions of one billionth of a meter, macroscopic field of view, or the capability to retrieve chemical or magnetic contrast, among other features.
Chang, Huibin +2 more
core +2 more sources
On the linear convergence of the alternating direction method of multipliers [PDF]
Mathematical Programming, 2016 We analyze the convergence rate of the alternating direction method of multipliers (ADMM) for minimizing the sum of two or more nonsmooth convex separable functions subject to linear constraints. Previous analysis of the ADMM typically assumes that the objective function is the sum of only two convex functions defined on two separable blocks of ...
Hong, Mingyi, Luo, Zhi-Quan
openaire +3 more sources
Alternating Direction Method of Multipliers for Generalized Low-Rank Tensor Recovery
Algorithms, 2016 Low-Rank Tensor Recovery (LRTR), the higher order generalization of Low-Rank Matrix Recovery (LRMR), is especially suitable for analyzing multi-linear data with gross corruptions, outliers and missing values, and it attracts broad attention in the fields
Jiarong Shi +3 more
doaj +1 more source
Bregman Alternating Direction Method of Multipliers
CoRR, 2013 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.
Huahua Wang, Arindam Banerjee 0001
openaire +3 more sources