Rizk, ElsaVlaski, StefanSayed, Ali H.2026-02-022026-02-022026-01-302023-01-0110.1109/ICASSP49357.2023.10095990https://infoscience.epfl.ch/handle/20.500.14299/258787WOS:001595432200077We study the generation of dependent random numbers in a distributed fashion in order to enable privatized distributed learning by networked agents. We propose a method that we refer to as local graph-homomorphic processing; it relies on the construction of particular noises over the edges to ensure a certain level of differential privacy. We show that the added noise does not affect the performance of the learned model. This is a significant improvement to previous works on differential privacy for distributed algorithms, where the noise was added in a less structured manner without respecting the graph topology and has often led to performance deterioration. We illustrate the theoretical results by considering a linear regression problem over a network of agents.Englishdistributed systemsdistributed learningdifferentialprivacyrandom number generatortext::conference output::conference proceedings::conference paper