mlsanityData to 7 Oct 2026

Generalized ADMM in Distributed Learning via Variational Inequality

arXiv 2104.12608 ↗First posted 26 Apr 2021cs.NI cs.DC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Due to the explosion in size and complexity of modern data sets and privacy concerns of data holders, it is increasingly important to be able to solve machine learning problems in distributed manners. The Alternating Direction Method of Multipliers (ADMM) through the concept of consensus variables is a practical algorithm in this context where its diverse variations and its performance have been studied in different application areas. In this paper, we study the effect of the local data sets of users in the distributed learning of ADMM. Our aim is to deploy variational inequality (VI) to attain an unified view of ADMM variations. Through the simulation results, we demonstrate how more general definitions of consensus parameters and introducing the uncertain parameters in distribute approach can help to get the better results in learning processes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 25 references that are in the map. First posted on arXiv 26 Apr 2021.

Builds on

10 of 25 references.

References · 10

  1. 2018COLA: Decentralized Linear Learningcited by 30
  2. 2019GADMM: Fast and Communication Efficient Framework for Distributed Machine Learningcited by 30
  3. 2015A General Analysis of the Convergence of ADMMcited by 22
  4. 2013Optimal parameter selection for the alternating direction method of multipliers (ADMM): quadratic problemscited by 19
  5. 2019Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learningcited by 17
  6. 2019L-FGADMM: Layer-Wise Federated Group ADMM for Communication Efficient Decentralized Deep Learningcited by 8
  7. 2015An Explicit Rate Bound for the Over-Relaxed ADMMcited by 2
  8. 2017Nonconvex Generalization of Alternating Direction Method of Multipliers for Nonlinear Equality Constrained Problemscited by 2
  9. 2019Distributed Inexact Successive Convex Approximation ADMM: Analysis-Part Icited by 1
  10. 2019Representation of Federated Learning via Worst-Case Robust Optimization Theorycited by 1

Built on by

Not cited yet.