 |
Center for Nonlinear Studies |
The max-product algorithm, which attempts to compute the maximizing assignment of a given objective function, 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 optimal assignment. In this talk, I will discuss a simple derivation of a new family of message passing algorithms. I will show 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. Additionally, I will provide an asynchronous message passing schedule that, under mild assumptions, guarantees the convergence of our algorithm. The theory will be motivated by applying these ideas to the ferromagnetic Ising model.
Host: Misha Chertkov