Federated Learning (FL) enables mobile phones to collaboratively learnashared prediction model while keeping all the training data on device, decoupling the ability to do machine learning from the need to store the data in the cloud. This goes beyond the use of local models that make predictions on mobile devices by bringing model training to the device as well.FL was co-invented by my former student Jakub Konecny, myself and Google. We have launched. a FL system in 2017, it is now in use in more than 1 billion Android devices:https://ai.googleblog.com/2017/04/federated-learning-collaborative.html https://ai.google/research/pubs/pub45648 In this project we will investigate further improvements and applications of FL.
Program - Computer Science
Division - Computer, Electrical and Mathematical Sciences and Engineering
Field of Study - Machine Learning
Professor, Computer Science<br/>
Prof. Richtarik's research interests lie at the intersection of mathematics, computer science, machine learning, optimization, numerical linear algebra, high performance computing and applied probability. He is interested in developing zero, first, and second-order algorithms for convex and nonconvex optimization problems described by big data, with a particular focus on randomized, parallel and distributed methods. He is the co-inventor of federated learning, a Google platform for machine learning on mobile devices preserving privacy of users' data.
Desired Project Deliverables
Ideally a joint research paper.