Postdoc • Penn
ndf96@seas.upenn.edu
I am a postdoctoral researcher at the University of Pennsylvania, where I work under the supervision of Prof. George Pappas.
My research interest is at the intersection of communication networks, control and machine learning.
My goal is to contribute to the methodological foundations of the next generation of distributed and multi-agent autonomous
systems. Engineering-wise, I am very interested in communication efficiency:
how can multiple agents coordinate with minimal communication cost to
achieve a certain objective? How can we design communication and control protocols accordingly?
Application-wise, I have recently been working intensively
on environmental monitoring in the context of multi-agent underwater robotics,
which to me represents a stimulating and challenging frontier of engineering and science.
Check out our recent project
on mapping the Douro river plume with underwater autonomous vehicles and multi-agent reinforcement learning.
I obtained my PhD from University of Padova, where I was advised by Prof. Luca Schenato and co-advised by Prof. Michele Rossi. During my PhD, my focus has been on studying the designs and properties of frameworks in which multiple agents cooperate to solve a machine learning (ML) or reinforcement learning (RL) problem by communicating with a central coordinator, in what is called the Federated Learning (FL) paradigm. Some of the research questions I tried to answer have been: can we get superlinear convergence in FL in a communication-efficient way? Is cooperation beneficial in federated RL when communication is subject to constraints? The typical fields of application of these studies are, for example, in large-scale distributed ML, FL over wireless networks, ML and RL algorithms trained from decentralized data at the network edge and 6G systems.
