Differentially Private Distributed Estimation and Learning

arXiv:2306.15865v5 Announce Type: replace
Abstract: We study distributed estimation and learning problems in a networked environment where agents exchange information to estimate unknown statistical properties of random variables from their privately observed samples. The agents can collectively estimate the unknown quantities by exchanging information about their private observations, but they also face privacy risks. Our novel algorithms extend the existing distributed estimation literature and enable the participating agents to estimate a complete sufficient statistic from private signals acquired offline or …

abstract agents arxiv cs.lg cs.si cs.sy distributed eess.sy environment face information math.st privacy random risks samples stat.ap statistical stat.ml stat.th study the unknown type variables