DATE:Thursday, September 5, 2019
TIME: 4:00 - 5:00 pm - NOTE TIME
PLACE: SCAIFE 125 - NOTE LOCATION CHANGE
SPEAKER: Brendan McMahan, Google
TITLE: Federated Learning, from Research to Practice [slides]
ABSTRACT:
Federated Learning enables mobile devices to collaboratively learn a shared prediction model while keeping all the training data on device, decoupling the ability to do machine learning from the need to collect and store the data in a central location. In this talk, I will discuss: how federated learning differs from more traditional machine learning paradigms; practical algorithms for federated learning that address the unique challenges of this setting; extensions to federated learning, including differential privacy, secure aggregation, and compression for model updates; federated learning applications and systems at Google; and finally a selection of exciting open problems and challenges in FL.
BIO:
Brendan McMahan is a research scientist at Google, where he leads efforts on decentralized and privacy-preserving machine learning. His team pioneered the concept of federated learning, and continues to push the boundaries of what is possible when working with decentralized data using privacy-preserving techniques. Previously, he has worked in the fields of online learning, large-scale convex optimization, and reinforcement learning. Brendan received his Ph.D. in computer science from Carnegie Mellon University.
SEMINAR HOST: Phil Gibbons
VISITOR COORDINATOR: Marcella L Baker <marcella@cs.cmu.edu>
SDI SEMINAR QUESTIONS?
Karen Lindenfelser, 86716, or visit www.pdl.cmu.edu/SDI/