Universaility
Presenter(s)

ISIT 2021, Melbourne, Victoria, Australia
Plenary Lecture

 

Date

Abstract

Information theory is based on probabilistic modeling of the sources and channels which define the information quantities like entropy and capacity and the associated coding schemes. However, in reality, these models are unknown and may even be nonexistent. Yet, practical communication systems work under uncertainty and varying conditions. The key capability to combat uncertainty is termed “universality”. Universal schemes adapt, learn, work, and can even be optimal, no matter what the model is. The universality concept will be presented in several basic communication problems:

  • Lossless source coding and the associated problem of universal prediction and learning;
  • Channel decoding and channel coding (which requires at least some feedback);
  • Joint source channel coding – a universal “hybrid analog-digital” solution recently received the scientific and engineering award of the academy of motion pictures (Oscar)