Summary; The paper studies the classical problem of estimating the probability mass function (pmf) of a discrete random variable given iid samples, but distributed among different nodes. The key quantity of interest is how much communication must be expended by each node (in a broadcast, but perhaps interactive, setting) to a central observer which then outputs the estimate of the underlying pmf. The main results of the paper areclearly stated and are easy to follow. The results mostly point out that in the worst case (i.e., no assumptions on the underlying pmf) there is nothing better for each node to do than to communicate its sample to the central observer. The paper addresses a central topic of a long line of recent works on distributed parameter estimation.

We study the problem of interactive function computation by multiple parties, each possessing a bit, in a differential privacy setting (i.e., there remains an uncertainty in any party's bit even when given the transcript of interactions and all the other parties' bits). Each party wants to compute a function, which could differ from party to party, and there could be a central observer interested in computing a separate function. Performance at each party is measured via the accuracy of the function to be computed. We allow for an arbitrary cost metric to measure the distortion between the true and the computed function values. Our main result is the optimality of a simple non-interactive protocol: each party randomizes its bit (sufficiently) and shares the privatized version with the other parties. This optimality result is very general: it holds for all types of functions, heterogeneous privacy conditions on the parties, all types of cost metrics, and both average and worst-case (over the inputs) measures of accuracy.

We study the problem of multi-party interactive function computation under differential privacy. In this setting, each party is interested in computing a function on its private bit and all the other parties' bits. The function to be computed can vary from one party to the other. Moreover, there could be a central observer who is interested in computing a separate function on all the parties' bits. Differential privacy ensures that there remains an uncertainty in any party's bit even when given the transcript of interactions and all other parties' bits. Performance at each party is measured via the accuracy of the function to be computed. We allow for an arbitrary cost metric to measure the distortion between the true and the computed function values. Our main result is the optimality of a simple non-interactive protocol: each party randomizes its bit (sufficiently) and shares the privatized version with the other parties. This optimality result is very general: it holds for all types of functions, heterogeneous privacy conditions on the parties, all types of cost metrics, and both average and worst-case (over the inputs) measures of accuracy.