Distributed Optimization: Achieving Communication Efficiency and Privacy Preservation Guarantees

Lecture / Panel
For NYU Community



Rikos Apostolos
Postdoctoral Associate, Systems Engineering, Boston University


"Distributed Optimization: Achieving Communication Efficiency and Privacy Preservation Guarantees"


The problem of distributed optimization has received extensive attention over recent years from the control and machine learning communities. However, for large-scale networks with possibly limited bandwidth capacity, communication overhead becomes a major bottleneck. Quantization of information is one of the major approaches to overcome this issue. In our presentation we will focus on the distributed optimization problem and its potential applications. We will present a distributed optimization algorithm which relies on gradient descent, and is combined with a finite time coordination algorithm where nodes are exchanging quantized messages. We will show that our proposed algorithm linearly converges to a neighborhood of the optimal solution, determined by the quantization level. Subsequently, we will present current developments on distributed learning with efficient communication. Then, we will present a privacy preservation protocol that guarantees privacy preservation while maintaining the efficiency of communication channels, and could be combined with the aforementioned optimization algorithm. We will analyze the topological conditions according to which our protocol guarantees privacy preservation. Finally, we conclude our presentation by outlining potential future directions.

About Speaker

I am a Postdoctoral associate at Boston University. I am working with Prof. Ioannis Paschalidis on networked control systems, and optimization with applications to epidemic networks. I received the B.Sc., M.Sc and Ph.D. degrees in Electrical Engineering from the Department of Electrical and Computer Engineering, University of Cyprus in 2010, 2012 and 2018 respectively. My supervisor was Prof. Christoforos N. Hadjicostis. My Ph.D. thesis focused on distributed control and coordination of multi agent networks, entitled ''Distributed Weight Balancing in Directed Topologies''. From November 2018 until January 2020, I joined KIOS Research and Innovation Center of Excellence in Cyprus as a research Lecturer. From February 2020 until February 2023, I joined KTH Royal Institute of Technology in Sweden as a Postdoctoral researcher. My supervisor was Prof. Karl Henrik Johansson. Since April 2023, I have been a Postdoctoral associate at Boston University.