Survey Propagation: Iterative Solutions to Constraint Satisfaction Problems

Iterative algorithms, such as the well known Belief Propagation algorithm, have had much success in solving problems in statistical inference and coding and information theory. Survey Propagation attempts to apply iterative message passing algorithms to solve difficult combinatorial problems, in particular constraint satisfaction problems such as k-sat and coloring problems. Intuition from statistical physics, involving evidence of phase transitions and clustering phenomena in the solution space, motivate some key modifications to well-known message passing algorithms, to yield effective tools for large instances of constraint satisfaction problems. The main algorithm, Survey Propagation, is motivated and developed, and then realized as a Belief Propagation algorithm, with an addition of a joker state.