Total Variation Minimization Perspective on Trustworthy Federated Learning
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only! Grab it Explore the concept of total variation (TV) minimization as a design principle for federated learning (FL) systems in this 51-minute lecture by Alex Jung from the Finnish Center for Artificial Intelligence. Dive into the computational and statistical aspects of TV minimization and its relevance to designing trustworthy FL systems. Learn how mainstream FL flavors, including personalized, clustered, vertical, and horizontal FL, can be derived as special cases of TV minimization. Gain insights from Jung, an accomplished computer science educator and researcher, as he shares his expertise on this crucial topic in machine learning and artificial intelligence.