中文
相关论文

相关论文: Extended Gauss-Newton and ADMM-Gauss-Newton Algori…

200 篇论文

We consider a class of structured, nonconvex, nonsmooth optimization problems under orthogonality constraints, where the objectives combine a smooth function, a nonsmooth concave function, and a nonsmooth weakly convex function. This class…

最优化与控制 · 数学 2025-01-14 Ganzhao Yuan

In this paper, we propose a new stochastic alternating direction method of multipliers (ADMM) algorithm, which incrementally approximates the full gradient in the linearized ADMM formulation. Besides having a low per-iteration complexity as…

机器学习 · 计算机科学 2013-08-19 Leon Wenliang Zhong , James T. Kwok

We introduce Newton-ADMM, a method for fast conic optimization. The basic idea is to view the residuals of consecutive iterates generated by the alternating direction method of multipliers (ADMM) as a set of fixed point equations, and then…

最优化与控制 · 数学 2017-06-21 Alnur Ali , Eric Wong , J. Zico Kolter

The alternating direction method of multipliers (ADMM) is an effective method for solving wide fields of convex problems. At each iteration, the classical ADMM solves two subproblems exactly. However, in many applications, it is expensive…

最优化与控制 · 数学 2019-03-07 Yan Gu , Nobuo Yamashita

In this paper, we propose and analyze an inexact version of the symmetric proximal alternating direction method of multipliers (ADMM) for solving linearly constrained optimization problems. Basically, the method allows its first subproblem…

最优化与控制 · 数学 2020-06-05 Vando A. Adona , Max L. N. Gonçalves

We present practical Levenberg-Marquardt variants of Gauss-Newton and natural gradient methods for solving non-convex optimization problems that arise in training deep neural networks involving enormous numbers of variables and huge data…

机器学习 · 计算机科学 2019-06-07 Yi Ren , Donald Goldfarb

In this paper, we propose a novel distributed algorithm for consensus optimization over networks and a robust extension tailored to deal with asynchronous agents and packet losses. Indeed, to robustly achieve dynamic consensus on the…

最优化与控制 · 数学 2025-09-04 Guido Carnevale , Nicola Bastianello , Giuseppe Notarstefano , Ruggero Carli

The alternating direction method of multipliers (ADMM) is a powerful splitting algorithm for linearly constrained convex optimization problems. In view of its popularity and applicability, a growing attention is drawn towards the ADMM in…

最优化与控制 · 数学 2022-08-19 Sedi Bartz , Rubén Campoy , Hung M. Phan

This paper studies efficient distributed optimization methods for multi-agent networks. Specifically, we consider a convex optimization problem with a globally coupled linear equality constraint and local polyhedra constraints, and develop…

系统与控制 · 计算机科学 2016-11-15 Tsung-Hui Chang

The alternating direction method of multipliers (ADMM) has been widely adopted in low-rank approximation and low-order model identification tasks; however, the performance of nonconvex ADMM is highly reliant on the choice of penalty…

最优化与控制 · 数学 2023-09-11 Qingyuan Liu , Zhengchao Huang , Hao Ye , Dexian Huang , Chao Shang

This paper proposes a provably convergent multiblock ADMM for nonconvex optimization with nonlinear dynamics constraints, overcoming the divergence issue in classical extensions. We consider a class of optimization problems that arise from…

最优化与控制 · 数学 2025-06-24 Bowen Li , Ya-xiang Yuan

In this paper, we propose a novel solution for non-convex problems of multiple variables, especially for those typically solved by an alternating minimization (AM) strategy that splits the original optimization problem into a set of…

机器学习 · 计算机科学 2022-06-28 Jingyuan Xia , Shengxi Li , Jun-Jie Huang , Imad Jaimoukha , Deniz Gunduz

Recently, minimax optimization received renewed focus due to modern applications in machine learning, robust optimization, and reinforcement learning. The scale of these applications naturally leads to the use of first-order methods.…

最优化与控制 · 数学 2023-03-07 Saeed Hajizadeh , Haihao Lu , Benjamin Grimmer

An inexact accelerated stochastic Alternating Direction Method of Multipliers (AS-ADMM) scheme is developed for solving structured separable convex optimization problems with linear constraints. The objective function is the sum of a…

最优化与控制 · 数学 2020-10-27 Jianchao Bai , William W. Hager , Hongchao Zhang

Support vector machines (SVMs) with sparsity-inducing nonconvex penalties have received considerable attentions for the characteristics of automatic classification and variable selection. However, it is quite challenging to solve the…

机器学习 · 统计学 2018-09-12 Lei Guan , Linbo Qiao , Dongsheng Li , Tao Sun , Keshi Ge , Xicheng Lu

In this paper, we propose a generalized alternating direction method of multipliers (ADMM) with semi-proximal terms for solving a class of convex composite conic optimization problems, of which some are high-dimensional, to moderate…

最优化与控制 · 数学 2018-01-17 Yunhai Xiao , Liang Chen , Donghui Li

In this paper, a stochastic alternating direction method of multipliers (ADMM) is proposed for a class of nonsmooth composite and stochastic convex optimization problems in Hilbert space, motivated by optimization problems constrained by…

最优化与控制 · 数学 2026-05-18 Weihua Deng , Haiming Song , Hao Wang , Jinda Yang

Inexact alternating direction multiplier methods (ADMMs) are developed for solving general separable convex optimization problems with a linear constraint and with an objective that is the sum of smooth and nonsmooth terms. The approach…

最优化与控制 · 数学 2016-04-12 William W. Hager , Hongchao Zhang

This paper aims to present a fairly accessible generalization of several symmetric Gauss-Seidel decomposition based multi-block proximal alternating direction methods of multipliers (ADMMs) for convex composite optimization problems. The…

最优化与控制 · 数学 2020-06-09 Liang Chen , Defeng Sun , Kim-Chuan Toh , Ning Zhang

In this paper, we study a class of non-convex optimization problems known as multi-affine quadratic equality constrained problems, which appear in various applications--from generating feasible force trajectories in robotic locomotion and…

最优化与控制 · 数学 2026-03-13 Yutong Chao , Michal Ciebielski , Jalal Etesami , Majid Khadiv