Toward Provably Private Federated Learning

In this talk from the Federated and Collaborative Learning Boot Camp, Daniel Ramage (Google) provided an overview of pioneering work at Google on federated learning, and discussed important open problems in the space. Ramage considered three questions at the heart of federated learning: How do we minimize the amount of user data sent to the server? How do we anonymize it while keeping it useful for learning? And perhaps most ambitiously, how do we prove to the user that their privacy was preserved?