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

arXiv:2404.14358v1 Announce Type: cross
Abstract: 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 …

abstract analysis arxiv continuous cs.lg framework general generalized key machine machine learning math.oc modern role scale stochastic type variants versions work