中文
相关论文

相关论文: A three-operator splitting perspective of a three-…

200 篇论文

The parallel alternating direction method of multipliers (ADMM) algorithms have gained popularity in statistics and machine learning due to their efficient handling of large sample data problems. However, the parallel structure of these…

统计理论 · 数学 2024-04-11 Xiaofei Wu , Jiancheng Jiang , Zhimin Zhang

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…

最优化与控制 · 数学 2021-03-02 Tianjian Huang , Prajwal Singhania , Maziar Sanjabi , Pabitra Mitra , Meisam Razaviyayn

Multi-block separable convex problems recently received considerable attention. This class of optimization problems minimizes a separable convex objective function with linear constraints. The algorithmic challenges come from the fact that…

最优化与控制 · 数学 2016-08-18 Qia Li , Yuesheng Xu , Na Zhang

In this paper, we review the parallel and distributed optimization algorithms based on the alternating direction method of multipliers (ADMM) for solving "big data" optimization problems in modern communication networks. We first introduce…

数值分析 · 计算机科学 2015-04-09 Lanchao Liu , Zhu Han

Learning to Optimize (L2O) approaches, including algorithm unrolling, plug-and-play methods, and hyperparameter learning, have garnered significant attention and have been successfully applied to the Alternating Direction Method of…

最优化与控制 · 数学 2024-09-27 Ling Liang , Cameron Austin , Haizhao Yang

We consider three challenges in multi-block Alternating Direction Method of Multipliers (ADMM): building convergence conditions for ADMM with any block (variable) sequence, finding available block sequences to be fit for ADMM, and designing…

系统与控制 · 计算机科学 2018-03-06 Jun Li , Hongfu Liu , Yue Wu , Yun Fu

In this paper, we develop a splitting algorithm incorporating Bregman distances to solve a broad class of linearly constrained composite optimization problems, whose objective function is the separable sum of possibly nonconvex nonsmooth…

最优化与控制 · 数学 2024-10-01 Tan Nhat Pham , Minh N. Dao , Andrew Eberhard , Nargiz Sultanova

We present an efficient alternating direction method of multipliers (ADMM) algorithm for segmenting a multivariate non-stationary time series with structural breaks into stationary regions. We draw from recent work where the series is…

机器学习 · 统计学 2018-06-26 Alex Tank , Emily B. Fox , Ali Shojaie

This article reports an algorithm for multi-agent distributed optimization problems with a common decision variable, local linear equality and inequality constraints and set constraints with convergence rate guarantees.…

系统与控制 · 电气工程与系统科学 2022-11-17 Vivek Khatana , Murti V. Salapaka

This paper considers decentralized consensus optimization problems where nodes of a network have access to different summands of a global objective function. Nodes cooperate to minimize the global objective by exchanging information with…

最优化与控制 · 数学 2016-09-21 Aryan Mokhtari , Wei Shi , Qing Ling , Alejandro Ribeiro

Motivated by big data applications, first-order methods have been extremely popular in recent years. However, naive gradient methods generally converge slowly. Hence, much efforts have been made to accelerate various first-order methods.…

最优化与控制 · 数学 2016-06-30 Yangyang Xu

The alternating direction method of multipliers (ADMM) is a popular approach for solving optimization problems that are potentially non-smooth and with hard constraints. It has been applied to various computer graphics applications,…

图形学 · 计算机科学 2019-09-04 Juyong Zhang , Yue Peng , Wenqing Ouyang , Bailin Deng

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 consider from two different aspects the proximal alternating direction method of multipliers (ADMM) in Hilbert spaces. We first consider the application of the proximal ADMM to solve well-posed linearly constrained…

最优化与控制 · 数学 2023-10-11 Qinian Jin

Alternating Direction Method of Multipliers (ADMM) is a popular algorithm for distributed learning, where a network of nodes collaboratively solve a regularized empirical risk minimization by iterative local computation associated with…

机器学习 · 计算机科学 2020-05-19 Zonghao Huang , Yanmin Gong

We propose both serial and parallel proximal (linearized) alternating direction method of multipliers (ADMM) algorithms for training residual neural networks. In contrast to backpropagation-based approaches, our methods inherently mitigate…

机器学习 · 计算机科学 2025-04-01 Jintao Xu , Yifei Li , Wenxun Xing

In the fields of statistics, machine learning, image science, and related areas, there is an increasing demand for decentralized collection or storage of large-scale datasets, as well as distributed solution methods. To tackle this…

最优化与控制 · 数学 2024-01-17 Bowen Li , Bin Shi

The framework of Integral Quadratic Constraints (IQC) reduces the computation of upper bounds on the convergence rate of several optimization algorithms to a semi-definite program (SDP). In the case of over-relaxed Alternating Direction…

机器学习 · 统计学 2018-03-06 Guilherme França , José Bento

Many modern computer vision and machine learning applications rely on solving difficult optimization problems that involve non-differentiable objective functions and constraints. The alternating direction method of multipliers (ADMM) is a…

计算机视觉与模式识别 · 计算机科学 2017-04-11 Zheng Xu , Mario A. T. Figueiredo , Xiaoming Yuan , Christoph Studer , Tom Goldstein

The alternating direction method of multipliers (ADMM) is widely used for solving large-scale semidefinite programs (SDPs), yet on instances with multiple primal-dual optimal solution pairs, it often enters prolonged slow-convergence…

最优化与控制 · 数学 2026-03-04 Shucheng Kang , Heng Yang