Technical Program

Paper Detail

Paper IDD.2.4
Paper Title Incremental ADMM with Privacy-Preservation for Decentralized Consensus Optimization
Authors Yu Ye, Hao Chen, Ming Xiao, Mikael Skoglund, KTH Royal institute of technology, Sweden; H. Vincent Poor, Princeton University, United States
Session D.2: Coding for Specialized Computations
Presentation Lecture
Track Coded and Distributed Computation
Manuscript  Click here to download the manuscript
Virtual Presentation  Click here to watch in the Virtual Symposium
Abstract The alternating direction method of multipliers (ADMM) has recently been recognized as a promising approach for large-scale machine learning models. However, very few results study ADMM from the aspect of communication costs, especially jointly with privacy preservation. We investigate the communication efficiency and privacy of ADMM in solving the consensus optimization problem over decentralized networks. We first propose incremental ADMM (I-ADMM), the updating order of which follows a Hamiltonian cycle. To protect privacy for agents against external eavesdroppers, we investigate I-ADMM with privacy preservation, where randomized initialization and step size perturbation are adopted. Using numerical results from simulations, we demonstrate that the proposed I-ADMM with step size perturbation can be both communication efficient and privacy preserving.

Plan Ahead


2021 IEEE International Symposium on Information Theory

11-16 July 2021 | Melbourne, Victoria, Australia

Visit Website!