Efficiently Searching for Frustrated Cycles in MAP Inference
نویسندگان
چکیده
Dual decomposition provides a tractable framework for designing algorithms for finding the most probable (MAP) configuration in graphical models. However, for many real-world inference problems, the typical decomposition has a large integrality gap, due to frustrated cycles. One way to tighten the relaxation is to introduce additional constraints that explicitly enforce cycle consistency. Earlier work showed that cluster-pursuit algorithms, which iteratively introduce cycle and other higherorder consistency constraints, allows one to exactly solve many hard inference problems. However, these algorithms explicitly enumerate a candidate set of clusters, limiting them to triplets or other short cycles. We solve the search problem for cycle constraints, giving a nearly linear time algorithm for finding the most frustrated cycle of arbitrary length. We show how to use this search algorithm together with the dual decomposition framework and clusterpursuit. The new algorithm exactly solves MAP inference problems arising from relational classification and stereo vision.
منابع مشابه
Developing a Model Based on Geospatial Information Systems (GIS) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for Providing the Spatial Distribution Map of Landslide Risk. Case Study: Alborz Province
Landslide is one of these natural hazards which causes a great amount of financial and human damage annually allover the world. Accordingly, identification of areas with landslide threat for implementation of preventive measures in order to confront against the instability of hillsides for reduction of potential threats and related risks is very important. In this research a new method for clas...
متن کاملA Fast and Exact Energy Minimization Algorithm for Cycle MRFs
The presence of cycles gives rise to the difficulty in performing inference for MRFs. Handling cycles efficiently would greatly enhance our ability to tackle general MRFs. In particular, for dual decomposition of energy minimization (MAP inference), using cycle subproblems leads to a much tighter relaxation than using trees, but solving the cycle subproblems turns out to be the bottleneck. In t...
متن کاملBudgeted Online Collective Inference
Updating inference in response to new evidence is a fundamental challenge in artificial intelligence. Many real problems require large probabilistic graphical models, containing millions of interdependent variables. For such large models, jointly updating the most likely (i.e., MAP) configuration of the variables each time new evidence is encountered can be infeasible, even if inference is trac...
متن کاملDynamic Planar-Cuts: Efficient Computation of Min-Marginals for Outer-Planar Models
This paper deals with Dynamic MAP Inference, where the goal is to solve an instance of the MAP problem given that we have already solved a related instance of the problem. We propose an algorithm for Dynamic MAP Inference in planar Ising models, called Dynamic Planar-Cuts. As an application of our proposed approach, we show that we can extend the MAP inference algorithm of Schraudolph and Kamen...
متن کاملDynamic Planar-Cuts: Efficient Computation of Min-Marginals for Outer-Planar MRFs
This paper presents an algorithm for Dynamic MAP inference and the computation of min-marginals in boolean outer-planar MRFs. Our goal is to efficiently solve an instance of the MAP problem given that we have already solved a related instance. As an example of Dynamic MAP inference, we consider the problem of computing minmarginals. The theoretical contribution of this paper is that we prove th...
متن کامل