Optimal federated learning under differential privacy constraints

Seminar in Mathematics

Abstract: With the growing computational power and increasing awareness of privacy, federated learning has emerged as a pivotal framework for private, distributed data analysis.  Depending on applications, diverse privacy constraints come into play, each imposing a unique cost on statistical accuracy.

In this talk, I will start with an overview of the foundational concept of differential privacy (DP).  I will then introduce three notions of DP tailored to the federated learning context, highlighting their relevance and implications in distributed settings.  The core focus of this talk will be on a functional data estimation problem under a hierarchical and heterogeneous DP framework. I will discuss how privacy constraints impact estimation accuracy and quantify these trade-offs through the lens of minimax theory. Key aspects of the proofs will also be outlined, as well as some numerical performances.