paper-with-me

홈 › Papers

A General Continuous-Time Formulation of Stochastic ADMM and Its Variants

2024-04-22 · Chris Junchi Li

Stochastic versions of the alternating direction method of multiplier (ADMM) and its variants play a key role in many modern large-scale machine learning problems. In this work, we introduce a unified algorithmic framework called generalized stochastic ADMM and investigate their continuous-time analysis. The generalized framework widely includes many stochastic ADMM variants such as standard, linearized and gradient-based ADMM. Our continuous-time analysis provides us with new insights into stochastic ADMM and variants, and we rigorously prove that under some proper scaling, the trajectory of stochastic ADMM weakly converges to the solution of a stochastic differential equation with small noise. Our analysis also provides a theoretical explanation of why the relaxation parameter should be chosen between 0 and 2.

📄 PDF Abstract BibTeX arXiv:2404.14358

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ADMM The alternating direction method of multipliers (ADMM) is an algorithm that solves convex optimization problems by breaking them into smaller pieces, each of which are…

Similar Papers 제목 키워드 기반

Stochastic Modified Equations for Continuous Limit of Stochastic ADMM

2020-03-07 · Xiang Zhou, Huizhuo Yuan, Chris Junchi Li, Qingyun Sun

Stochastic version of alternating direction method of multiplier (ADMM) and its variants (linearized ADMM, gradient-based ADMM) plays a key role for modern large scale machine learning problems. One example is the regula…

Fast Stochastic Alternating Direction Method of Multipliers

2013-08-16 · Leon Wenliang Zhong, James T. Kwok

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-ite…

Scalable Stochastic Alternating Direction Method of Multipliers

2015-02-12 · Shen-Yi Zhao, Wu-Jun Li, Zhi-Hua Zhou

Stochastic alternating direction method of multipliers (ADMM), which visits only one sample or a mini-batch of samples each time, has recently been proved to achieve better performance than batch ADMM. However, most stoc…

Accelerated Variance Reduced Stochastic ADMM

2017-07-11 · Yuanyuan Liu, Fanhua Shang, James Cheng

Recently, many variance reduced stochastic alternating direction method of multipliers (ADMM) methods (e.g.\ SAG-ADMM, SDCA-ADMM and SVRG-ADMM) have made exciting progress such as linear convergence rates for strongly co…

Stochastic Alternating Direction Method of Multipliers with Variance Reduction for Nonconvex Optimization

2016-10-10 · Feihu Huang, Songcan Chen, Zhaosong Lu

In the paper, we study the stochastic alternating direction method of multipliers (ADMM) for the nonconvex optimizations, and propose three classes of the nonconvex stochastic ADMM with variance reduction, based on diffe…