Communication-Constrained Private Decentralized Online Personalized Mean Estimation
By: Yauhen Yakimenka , Hsuan-Yin Lin , Eirik Rosnes and more
Potential Business Impact:
Helps computers learn together while keeping secrets.
We consider the problem of communication-constrained collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific distributions. A consensus-based algorithm is studied under the framework of differential privacy in order to protect each agent's data. We give a theoretical convergence analysis of the proposed consensus-based algorithm for any bounded unknown distributions on the agents' data, showing that collaboration provides faster convergence than a fully local approach where agents do not share data, under an oracle decision rule and under some restrictions on the privacy level and the agents' connectivity, which illustrates the benefit of private collaboration in an online setting under a communication restriction on the agents. The theoretical faster-than-local convergence guarantee is backed up by several numerical results.
Similar Papers
Privacy-Preserving Distributed Estimation with Limited Data Rate
Systems and Control
Keeps secrets safe while sending less data.
Local Differential Privacy for Distributed Stochastic Aggregative Optimization with Guaranteed Optimality
Systems and Control
Lets computers learn together privately and accurately.
Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation
Cryptography and Security
Keeps private data safe in shared computer groups.