Differentially Private Database Release via Kernel Mean Embeddings

We aim to contribute to the body of research on the tradeoff between releasing datasets from which publicly beneficial statistical inferences can be drawn, and between protecting the privacy of individuals who contribute to such datasets. Currently the most successful formalization of protecting user privacy is provided by differential privacy [Dwork and Roth, 2014], which is a definition that any algorithm operating on a database may or may not satisfy. An algorithm that does satisfy the definition ensures that a particular individual does not lose too much privacy by deciding to contribute to the database on which the algorithm operates. While differentially private algorithms for releasing entire databases have been studied previously [Blum et al., 2008, Wasserman and Zhou, 2010, Zhou et al., 2009], most algorithms focus on releasing a privacy-protected version of a particular summary statistic, or of a statistical model trained on the private dataset. In this work we revisit the more difficult non-interactive, or offline setting, where the database owner aims to release a privacy-protected version of the entire database without knowing what statistics third-parties may wish to compute in the future.