Dynamics based privacy preservation in decentralized optimization
Dynamics based privacy preservation in decentralized optimization
复制标题
DOI：
10.1016/j.automatica.2023.110878
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Huan Gao;Yongqiang Wang;Angelia Nedi'c
中科院分区：
文献类型：
--
作者：
Huan Gao;Yongqiang Wang;Angelia Nedi'c
随着去中心化优化在机器学习、控制和机器人等各个领域的应用不断增加，其隐私也受到越来越多的关注。现有的去中心化优化隐私解决方案通过修补差异隐私或同态加密等信息技术隐私机制来实现隐私，这要么牺牲优化精度，要么产生大量计算/通信开销。我们通过利用去中心化优化动态的鲁棒性，提出了一种本质上保护隐私的去中心化优化算法。更具体地说，我们提出了一个通用的去中心化优化框架，基于该框架，我们表明可以通过在优化参数中添加随机性来保护参与节点梯度的隐私。我们进一步表明，添加的随机性对优化的准确性没有影响，并证明当全局目标函数平滑且强凸时，我们固有的隐私保护算法具有 R 线性收敛。我们还证明了所提出的算法可以避免一个节点的梯度被其他节点推断。仿真结果证实了理论预测。
With decentralized optimization having increased applications in various domains ranging from machine learning, control, to robotics, its privacy is also receiving increased attention. Existing privacy solutions for decentralized optimization achieve privacy by patching information-technology privacy mechanisms such as differential privacy or homomorphic encryption, which either sacrifices optimization accuracy or incurs heavy computation/communication overhead. We propose an inherently privacy-preserving decentralized optimization algorithm by exploiting the robustness of decentralized optimization dynamics. More specifically, we present a general decentralized optimization framework, based on which we show that the privacy of participating nodes’ gradients can be protected by adding randomness in optimization parameters. We further show that the added randomness has no influence on the accuracy of optimization, and prove that our inherently privacy-preserving algorithm has R-linear convergence when the global objective function is smooth and strongly convex. We also prove that the proposed algorithm can avoid the gradient of a node from being inferable by other nodes. Simulation results confirm the theoretical predictions.