Lagrangian Relaxation for MAP Estimation in Graphical Models

Details Lagrangian Relaxation for MAP Estimation in Graphical Models Lagrangian Relaxation for MAP Estimation in Graphical Models

2007-09-28

arxiv.org/abs/0710.0013v1

Computer Science

Artificial Intelligence

10 pages, presented at 45th Allerton conference on communication, control and computing, to appear in proceedings

Scientific paper

We develop a general framework for MAP estimation in discrete and Gaussian graphical models using Lagrangian relaxation techniques. The key idea is to reformulate an intractable estimation problem as one defined on a more tractable graph, but subject to additional constraints. Relaxing these constraints gives a tractable dual problem, one defined by a thin graph, which is then optimized by an iterative procedure. When this iterative optimization leads to a consistent estimate, one which also satisfies the constraints, then it corresponds to an optimal MAP estimate of the original model. Otherwise there is a ``duality gap'', and we obtain a bound on the optimal solution. Thus, our approach combines convex optimization with dynamic programming techniques applicable for thin graphs. The popular tree-reweighted max-product (TRMP) method may be seen as solving a particular class of such relaxations, where the intractable graph is relaxed to a set of spanning trees. We also consider relaxations to a set of small induced subgraphs, thin subgraphs (e.g. loops), and a connected tree obtained by ``unwinding'' cycles. In addition, we propose a new class of multiscale relaxations that introduce ``summary'' variables. The potential benefits of such generalizations include: reducing or eliminating the ``duality gap'' in hard problems, reducing the number or Lagrange multipliers in the dual problem, and accelerating convergence of the iterative optimization procedure.

Affiliated with

Also associated with

No associations

Rating

Lagrangian Relaxation for MAP Estimation in Graphical Models does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Lagrangian Relaxation for MAP Estimation in Graphical Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Lagrangian Relaxation for MAP Estimation in Graphical Models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-461836