[Colloquium] Reminder - Ted Shao MS Presentation/Apr 10, 2023

[Megan Woodward]

This is an announcement of Ted Shao's MS Presentation
===============================================
Candidate: Ted Shao

Date: Monday, April 10, 2023

Time:  2:30 pm CST

Location: JCL 223

M.S. Paper Title: EdgeServe: An Execution Layer for Decentralized Prediction

Abstract: The relevant features for a machine learning task may be aggregated from data sources collected on different nodes in a network. This problem, which we call decentralized prediction, creates a number of interesting systems challenges in managing data routing, model placement, and time-synchronization. This paper presents EdgeServe, a machine learning system that can serve decentralized predictions. EdgeServe relies on a low-latency message broker to route data through a network to nodes that can serve predictions. EdgeServe relies on a series of novel optimizations that can trade-off computation, communication, and accuracy.

Advisors: Sanjay Krishnan

Committee Members: Michael Franklin, Sanjay Krishnan, and Nick Feamster