arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2003.10615math.OCcs.DC
收藏

分布式共识Optimization的隐私保护增量ADMM

Privacy-preserving Incremental ADMM for Decentralized Consensus Optimization

Yu Ye, Hao Chen, Ming Xiao, Mikael Skoglund, H. Vincent Poor

摘要:

乘法器的交替方向法(ADMM)最近被认为是大规模机器学习模型的有前途的优化器。然而,有很少的结果研究ADMM从通信成本方面,特别是结合隐私保护,这是分布式学习的关键。通过求解分散网络上的一致性最优化问题,研究了ADMM的通信效率和隐私保护。由于步行算法可以减少通信负载,我们首先提出了增量ADMM(I-ADMM)的基础上的步行算法,其更新顺序遵循一个哈密顿圈。然而,I-ADMM不能保证隐私的代理对外部窃听者,即使随机初始化应用。为了保护代理的隐私,我们提出了两个隐私保护的增量ADMM算法,即,PI-ADMM 1和PI-ADMM 2,其中分别采用对步长和原始变量的扰动。通过理论分析,证明了PI-ADMM 1算法的收敛性和隐私保护性,并通过数值实验进一步验证了算法的有效性。此外,仿真结果表明,提出的PI-ADMM 1和PI-ADMM 2算法是通信效率与国家的最先进的方法相比。

英文摘要:

The alternating direction method of multipliers (ADMM) has been recently recognized as a promising optimizer for large-scale machine learning models. However, there are very few results studying ADMM from the aspect of communication costs, especially jointly with privacy preservation, which are critical for distributed learning. We investigate the communication efficiency and privacy-preservation of ADMM by solving the consensus optimization problem over decentralized networks. Since walk algorithms can reduce communication load, we first propose incremental ADMM (I-ADMM) based on the walk algorithm, the updating order of which follows a Hamiltonian cycle instead. However, I-ADMM cannot guarantee the privacy for agents against external eavesdroppers even if the randomized initialization is applied. To protect privacy for agents, we then propose two privacy-preserving incremental ADMM algorithms, i.e., PI-ADMM1 and PI-ADMM2, where perturbation over step sizes and primal variables is adopted, respectively. Through theoretical analyses, we prove the convergence and privacy preservation for PI-ADMM1, which are further supported by numerical experiments. Besides, simulations demonstrate that the proposed PI-ADMM1 and PI-ADMM2 algorithms are communication efficient compared with state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑