Research seminar series - Distributed Optimization over Communication-constrained Networks: Enabling the Next Generation Machine Intelligence

Share

Research seminar series organized by Sensors Council, Vehicular Technology Society, and Communications Society Singapore Chapter

In today's networked world, enormous amounts of data are being collected by edge devices in a distributed fashion. It is often preferred to keep the data localized on the edge devices themselves for privacy concerns, fault-resilience, or the sheer communication expense of centrally aggregating the available data. As a consequence, there has been a rapid emergence of decentralized computational strategies in which global learning tasks are accomplished only through local processing. It this talk we shall review some topics in the decentralized optimization setting in which multiple nodes in a network collaborate to minimize the sum of their local loss functions.

We will consider both the centralized learning paradigm (a.k.a. federated learning) and the fully distributed paradigm. In both cases, we will introduce the relevant communication constraint for instance (i) a finite rate-constraint on the signal transmitted by any node, (ii) additive noise corrupting the signal received by any node, and (iii) straggling due to networking. We will review some of the techniques proposed in the literature to address such constraint, as well as some of my contributions on this topic.  The talk will conclude with some interesting research directions at the intersection of distributed optimization and wireless communication.



  Date and Time

  Location

  Hosts

  Registration



  • Date: 12 Nov 2021
  • Time: 03:00 PM to 04:00 PM
  • All times are Singapore
  • Add_To_Calendar_icon Add Event to Calendar

Meeting URL:     https://singaporetech.zoom.us/j/97702575888 

Meeting ID:         977 0257 5888

Passcode:            128102

  • Singapore
  • Singapore

  • Starts 01 November 2021 08:00 AM
  • Ends 12 November 2021 04:00 PM
  • All times are Singapore
  • No Admission Charge


  Speakers

Stefano Rini of National Yang Ming Chiao Tung University (NYCU), Taiwan

Topic:

Distributed Optimization over Communication-constrained Networks: Enabling the Next Generation Machine Intelligence

Biography:

Stefano Rini is an Associate Professor at the Department of Electrical and Computer Engineering at the National Yang Ming Chiao Tung University (NYCU) (previously National Chiao-Tung University (NCTU)), Hsinchu, Taiwan. He received the B.A. degree in computer science from the Politecnico di Milano, Italy, in 2005, the M.S. degree in both Electrical and Computer Engineering and Statistics from the University of Illinois at Chicago (UIC) in 2009. He earned his doctoral degree in Electrical and Computer Engineering at the University of Illinois in Chicago (UIC), USA, in 2011 under the supervision of Professor Tuninetti and co-adviser Professor Devroye, with a thesis titled "Cognition and Cooperation in Wireless Networks: an Information Theoretic Perspective". In 2012, he was a postdoctoral fellow at the Institute for Communications Engineering at the Technical University of Munich (TUM), Germany with Professor Kramer. In 2013 he was a postdoctoral fellow at the Department of Electrical Engineering at Stanford University, USA, with Professor Goldsmith. In 2014 he joined NCTU.