CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2010 vol.32 Issue No.08 - August

Subscribe

Issue No.08 - August (2010 vol.32)

pp: 1474-1488

Tomáš Werner , Czech Technical University, Praha

ABSTRACT

We present a number of contributions to the LP relaxation approach to weighted constraint satisfaction (= Gibbs energy minimization). We link this approach to many works from constraint programming, which relation has so far been ignored in machine vision and learning. While the approach has been mostly considered only for binary constraints, we generalize it to n-ary constraints in a simple and natural way. This includes a simple algorithm to minimize the LP-based upper bound, n-ary max-sum diffusion—however, we consider using other bound-optimizing algorithms as well. The diffusion iteration is tractable for a certain class of high-arity constraints represented as a black box, which is analogical to propagators for global constraints CSP. Diffusion exactly solves permuted n-ary supermodular problems. A hierarchy of gradually tighter LP relaxations is obtained simply by adding various zero constraints and coupling them in various ways to existing constraints. Zero constraints can be added incrementally, which leads to a cutting-plane algorithm. The separation problem is formulated as finding an unsatisfiable subproblem of a CSP.

INDEX TERMS

Weighted constraint satisfaction, Gibbs distribution, graphical model, Markov random field, linear programming relaxation, marginal polytope, cut polytope, cutting-plane algorithm, global constraint, supermodularity, tree-reweighted max-product.

CITATION

Tomáš Werner, "Revisiting the Linear Programming Relaxation Approach to Gibbs Energy Minimization and Weighted Constraint Satisfaction",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.32, no. 8, pp. 1474-1488, August 2010, doi:10.1109/TPAMI.2009.134REFERENCES