Motivated by the problem of next word prediction on user devices we introduce and study the problem of personalized frequency histogram estimation in a federated setting. In this problem, over some domain, each user observes a number of samples from a distribution which is specific to that user. The goal is to compute for all users a personalized estimate of the user’s distribution with error measured in KL divergence. We focus on addressing two central challenges: statistical heterogeneity and protection of user privacy. Our approach to the problem relies on discovering and exploiting similar…
Source: Read MoreÂ
