Seminars & Colloquia
Massachusetts Institute of Technology (MIT)
"Learning with Distributed Systems: Adversary-Resilience"
Thursday November 14, 2019 09:30 AM
Location: 3211, EB2 NCSU Centennial Campus
(Visitor parking instructions)
FL is a new distributed learning paradigm proposed by Google. The goal of FL is to enable the cloud (i.e., the learner) to train a model without collecting the training data from users' mobile devices. Compared with traditional learning, FL suffers serious security issues and several practical constraints call for new security Strategies. Towards quantitative and systematic insights into the impacts of those security issues, we formulated and studied the problem of Byzantine-resilient Federated Learning. We proposed two robust learning rules that secure gradient descent against Byzantine faults. The estimation error achieved under our more recently proposed rule is order-optimal in the minimax sense.
Host: Frank Mueller, CSC