Approximation Bounds for Inference using Cooperative Cuts

We analyze a family of probability distributions that are characterized by an embedded combinatorial structure. This family includes models having arbitrary treewidth and arbitrary sized factors. Unlike general models with such freedom, where the "most probable explanation" (MPE) problem is inapproximable, the combinatorial structure within our model, in particular the indirect use of sub-modularity, leads to several MPE algorithms that all have approximation guarantees.

[1]  E. L. Lawler,et al.  Computing Maximal "Polymatroidal" Network Flows , 1982, Math. Oper. Res..

[2]  László Lovász,et al.  Submodular functions and convexity , 1982, ISMP.

[3]  Éva Tardos,et al.  Layered Augmenting Path Algorithms , 1986, Math. Oper. Res..

[4]  Satoru Fujishige,et al.  Submodular functions and optimization , 1991 .

[5]  M. R. Rao,et al.  Combinatorial Optimization , 1992, NATO ASI Series.

[6]  William J. Cook,et al.  Combinatorial optimization , 1997 .

[7]  Ashraf M. Abdelbar,et al.  Approximating MAPs for Belief Networks is NP-Hard and Other Theorems , 1998, Artif. Intell..

[8]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[9]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[10]  Jack Edmonds,et al.  Submodular Functions, Matroids, and Certain Polyhedra , 2001, Combinatorial Optimization.

[11]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Fabián A. Chudak,et al.  Efficient solutions to relaxations of combinatorial problems with submodular penalties via the Lovász extension and non-smooth convex optimization , 2007, SODA '07.

[13]  Lisa Fleischer,et al.  Submodular Approximation: Sampling-based Algorithms and Lower Bounds , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[14]  Alper Atamtürk,et al.  Polymatroids and mean-risk minimization in discrete optimization , 2008, Oper. Res. Lett..

[15]  Venkat Chandrasekaran,et al.  Complexity of Inference in Graphical Models , 2008, UAI.

[16]  Satoru Iwata,et al.  Submodular Function Minimization under Covering Constraints , 2009, 2009 50th Annual IEEE Symposium on Foundations of Computer Science.

[17]  Vahab S. Mirrokni,et al.  Approximating submodular functions everywhere , 2009, SODA.

[18]  Christos Koufogiannakis,et al.  Greedy D{\ensuremath{\Delta}}-Approximation Algorithm for Covering with Arbitrary Constraints and Submodular Cost , 2009, ICALP.

[19]  J. Bilmes,et al.  Cooperative Cuts: Graph Cuts with Submodular Edge Weights , 2010 .

[20]  David B. Shmoys,et al.  Maximizing the Spread of Cascades Using Network Design , 2010, UAI.

[21]  Jin-Yi Cai,et al.  Approximation and hardness results for label cut and related problems , 2009, J. Comb. Optim..

[22]  Jeff A. Bilmes,et al.  Submodularity beyond submodular energies: Coupling edges in graph cuts , 2011, CVPR 2011.

[23]  Christos Koufogiannakis,et al.  Greedy Δ-Approximation Algorithm for Covering with Arbitrary Constraints and Submodular Cost , 2013, Algorithmica.