Machine Learning over Networks: From Fundamentals to Applications.

In this talk, we review sample results based on our recent work in the areas of machine learning
over networks and edge intellligence. In particular, we touch upon our work on communication-efficient federated learning and its applications.
In the first part of the talk, we shed light on topics pertaining to federated learning. First, we overview a second-order federated learning algorithm, coined Fed-Sophia, with communication and computation efficiency merits. Next, we introduce our recent work on second order state synchronization (SOSS) to address the limitations of Fed-Sophia with non-IID data. Afterwards we overview MIRA which proposes a novel approach of federated multi-task learning for fine-tuning LLMs.
In the second part of the talk, we shift focus to edge intelligence applications in digital health with particular focus on CVD prediction. Finally, we present our work on architecting, designing and demonstrating a system prototype for multi-tier intelligence for IoT.
Speaker(s): Dr. Tamer ElBatt
Agenda:
3 PM to 4 PM: Networking
4 PM to 4:45 PM: Presentation
4:45 PM to 5:30 PM: Q&A
5:30 PM to 6:30 PM: Networking
Room: 1308, Bldg: Sobrato Campus for Discovery and Innovation, 500 El Camino Real, Santa Clara, California, United States, 95053