Active Learning and Optimization for Next Generation Communication Networks

Network management and configuration is an essential attribute of any wireless network with reliable self-tuning capabilities.  In contrast to the past generations of networking solutions, on the other hand, in the ever-increasingly mobile and large-scale networks of tomorrow the network reconfiguration overhead may not be insignificant; this includes the initial beam alignment, link maintenance, spectrum sensing, packet resizing, etc. Our work aims to provide fundamental limits on the overhead associated with learning, network tuning, and optimization of network parameters. Our approach relies on the theory of active learning and optimization to quantify the networking overhead and utilizes recent data analytic and machine learning algorithms to develop practical learning/optimization algorithms. 

 In the first part of the talk, we consider the problem of search and optimization of the directional link establishment and maintenance (beam alignment) in mmWave communications. In the second part of the talk, we consider an important variant of the search problem: data-driven and empirical optimization for wireless network parameter tuning.

Speaker(s): Prof. Tara Javidi, ECE Dpt. UC San Diego,

Agenda:

6:00 PM Social; 6:30 PM Dinner/Presentation; 8:45 PM Wrap-up

Location:
Room: Ask for IEEE room at front counter
Bldg: The Doubletree Club – Orange County Airport
7 Hutton Centre Drive
Santa Ana, California
92707