In the last decade, there have been an increasing convergence of interest and methods between theoretical physics and fields as diverse as probability, machine learning, optimization and compressed sensing. In particular, many theoretical and applied works in statistical physics and computer science have relied on the use of message passing algorithms and their connection to statistical physics of glasses and spin glasses. The aim of this school, especially adapted to PhD students, post-docs, and young researchers, is to present the background necessary for entering this fast developing field.

The school will cover background necessary to understand the statistical physics and information theory techniques and methods, in particular inference, computational complexity, message passing algorithms, cavity and replica calculations (first week) as well as to become familiar with the most important applications of these techniques (second week). An important aim is to attract audience not only from physics but also from combinatorics, probability, computer science, machine learning and information theory.

Specific topics will include:

  • Statistical Inference and Learning
  • Compressed sensing and sparse reconstruction
  • Applications of Belief Propagation and Message Passing Algorithms
  • Random Satisfiability and Combinatorial Optimization
  • Error-correcting codes
  • Phase Transitions, the replica and cavity approaches