Nathaniel Hudson, Ph.D.

A brief introduction.


312 John Crerar Library

5730 S Ellis Ave

Chicago, IL 60637

I am a computer scientist, currently serving as a Postdoctoral Scholar at Globus Labs out of the University of Chicago’s Department of Computer Science.

A high-level description of my research is the design of systems for serving AI on edge computing infrastructure — i.e., Edge Intelligence (EI) — for smart city applications. More specifically, my research centers around challenges related to resource limitations available at the edge for supporting EI. Trade-offs between latency, accuracy, resource usage, etc. are common themes in my work.

Some areas of study my research touches include (but are not limited to):

  • federated learning
  • service placement and request scheduling
  • lossy compression techniques
  • social mining
  • modeling of information diffusion processes
  • interdependent and complex networks
  • cyber-physical systems

recent news

Sep 28, 2023 I will be giving a talk on federated learning on the Globus Compute platform on October 13th, 2023 as part of the Rural AI Workshop on Serverless Federated Learning for Remote Internet-of-Things Applications (click here to learn how to attend).
Aug 26, 2023 A paper exploring the adversarial prediction in federated learning processes has been accepted for publication in the 2023 IEEE World Forum of Internet-of-Things (WF-IoT) conference. It is also available on arXiv.
Aug 2, 2023 I am excited to, once again, serve as a TPC member for the 2023 IEEE DCOSS-IoT conference.
Mar 16, 2023 Work-in-Progress (WiP) paper won the Best Paper Award for the WiP session at the 2023 IEEE PerCom conference.
Feb 27, 2023 I am thrilled to once again be serving as a TPC member for the 2023 IEEE SECON conference.
Jan 11, 2023 I will be serving as a TPC member for the 2023 IEEE EDGE conference.
Jan 5, 2023 Short paper on balancing trade-offs in federated learning has been accepted for the Work-in-Progress session of the 2023 IEEE PerCom Conference in Atlanta, GA.
Nov 1, 2022 I will be attending the 2022 ACM/IEEE Supercomputing Conference in Dallas Texas.
Sep 26, 2022 I will be serving as a TPC member for the 2023 IEEE DCOSS-IoT conference.
Sep 1, 2022 I will serve as a TPC member for the 2023 IEEE PerCom Work-In-Progress (WIP) session.

selected publications

  1. “Smart Edge-Enabled Traffic Light Control: Improving Reward-Communication Trade-offs with Federated Reinforcement Learning”
    Hudson, Nathaniel, Oza, Pratham,  Khamfroush, Hana and 1 more author
    In 2022 IEEE International Conference on Smart Computing (SMARTCOMP) Jul 2022
  2. ICCCN
    “QoS-Aware Placement of Deep Learning Services on the Edge with Multiple Service Implementations”
    Hudson, NathanielKhamfroush, Hana,  and Lucani, Daniel E.
    In 2021 IEEE International Conference on Computer Communications and Networks (ICCCN) Big Data and Machine Learning for Networking (BDMLN) Workshop Jul 2021
  3. TNSE
    “Behavioral Information Diffusion for Opinion Maximization in Online Social Networks”
    Hudson, Nathaniel,  and Khamfroush, Hana
    IEEE Transactions on Network Science and Engineering (TNSE) Oct 2020