Approximation Bounds for Inference using Cooperative Cuts
نویسندگان
چکیده
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 submodularity, leads to several MPE algorithms that all have approximation guarantees.
منابع مشابه
Combinatorial problems with submodular coupling in machine learning and computer vision
Numerous problems in machine learning and computer vision are discrete. As a complicating factor, they often involve large data sets and higher-order interactions between elements in the data. For example, segmenting an image into foreground and background requires assigning a label to each pixel in the image. As object and background commonly have significant wide-range coherency, the most pro...
متن کاملBethe Bounds and Approximating the Global Optimum
Inference in general Markov random fields (MRFs) is NP-hard, though identifying the maximum a posteriori (MAP) configuration of pairwise MRFs with submodular cost functions is efficiently solvable using graph cuts. Marginal inference, however, even for this restricted class, is in #P. We prove new formulations of derivatives of the Bethe free energy, provide bounds on the derivatives and bracke...
متن کاملMulti-label cooperative cuts
Recently, a family of global, non-submodular energy functions has been proposed that is expressed as coupling edges in a graph cut. This formulation provides a rich modelling framework and also leads to efficient approximate inference algorithms. So far, the results addressed binary random variables. Here, we extend these results to the multi-label case, and combine edge coupling with move-maki...
متن کاملOn the bounds in Poisson approximation for independent geometric distributed random variables
The main purpose of this note is to establish some bounds in Poisson approximation for row-wise arrays of independent geometric distributed random variables using the operator method. Some results related to random sums of independent geometric distributed random variables are also investigated.
متن کاملSemideenite Programs and Combinatorial Optimization
Outline 1. Introductory examples: Shannon capacity and maximum cuts. 2. Preliminaries: linear programming, semideenite matrices. 3. General properties of semideenite programs: equivalent forms, Farkas Lemma, Duality Theorem, Ellipsoid method, Interior point method. 4. Getting semideenite programs I: eigenvalues of graphs and the method of variables. 5. Getting semideenite programs II: geometric...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011