Hu, PingBordignon, VirginiaVlaski, StefanSaye, Ali H.2023-01-162023-01-162023-01-162022-01-0110.1109/ICASSP43922.2022.9746784https://infoscience.epfl.ch/handle/20.500.14299/193734WOS:000864187906028This paper investigates the effect of combination policies on the performance of adaptive social learning in non-stationary environments. By analyzing the relation between the error probability and the underlying graph topology, we prove that in the slow adaptation regime, combination policies with a uniform Perron eigenvector will provide the smallest steady-state error probability. This result indicates that in terms of learning accuracy, doubly-stochastic combination policies yield optimal performance. Moreover, we estimate the adaptation time of adaptive social learning in the small signal-to-noise regime and show that in this regime, the influence of combination policies on the adaptation time is insignificant.AcousticsComputer Science, Artificial IntelligenceEngineering, Electrical & ElectronicComputer ScienceEngineeringsocial learningcombination policylarge deviationsadaptation timenetworkstext::conference output::conference proceedings::conference paper