Frequency estimation under local differential privacy

Private collection of statistics from a large distributed population is an important problem, and has led to scale deployments several leading technology companies. The dominant approach requires each user randomly perturb their input, guarantees in the local differential privacy model. In this paper, we place various approaches that have been suggested into common framework, perform extensive series experiments understand tradeoffs between different implementation choices. Our conclusion for core problems frequency estimation heavy hitter identification, careful choice algorithms can lead very effective solutions millions users.