Séminaire de Statistique et Optimisation

Private estimation from users’ data

by Clément Lalanne (TSE)

Salle K. Johnson, 1er étage (1R3)

Salle K. Johnson, 1er étage



Learning from users’ data has demonstrated to be tremendously effective at solving many real-world problems. However, such paradigm comes with new challenges such as users’ privacy. Differential Privacy was proposed as a way to bound the information quantity leaked by statistics in order to bound the power of membership tests, hence giving strong guarantees for users’ privacy. Being a rather strong constraint, it comes at a cost on the quality of estimation. A natural question is thus to quantify this cost, and to compare it to the already-existing sampling noise. In this presentation, we will see a generic way to quantify this cost via coupling arguments, and we will illustrate it by examples ranging from simple Bernoulli estimation to nonparametric density estimation.