Convergent and correct message passing schemes for optimization problems over graphical models
Nicholas Ruozzi, Sekhar Tatikonda · Uncertainty in Artificial Intelligence · 2010
The max-product algorithm, which attempts to compute the most probable assignment (MAP) of a given probability distribution, has recently found applications in quadratic minimization and combinatorial optimization. Unfortunately, the max-product algorithm is not guaranteed to converge and, even if it does, is not guaranteed to produce the MAP assignment. In this work, we provide a simple derivation of a new family of message passing algorithms by splitting the factors of our graphical model. We prove that, for any objective function that attains its maximum value over its domain, this new family of message passing algorithms always contains a message passing scheme that guarantees correctness upon convergence to a unique estimate. Finally, we adopt an asynchronous message passing schedule and prove that, under mild assumptions, such a schedule guarantees the convergence of our algorithm.