A Spectral Approach to Analysing Belief Propagation for 3-Colouring
نویسندگان
چکیده
Belief Propagation (BP) is a message-passing algorithm that computes the exact marginal distributions at every vertex of a graphical model without cycles. While BP is designed to work correctly on trees, it is routinely applied to general graphical models that may contain cycles, in which case neither convergence, nor correctness in the case of convergence is guaranteed. Nonetheless, BP gained popularity as it seems to remain effective in many cases of interest, even when the underlying graph is “far” from being a tree. However, the theoretical understanding of BP (and its new relative Survey Propagation) when applied to CSPs is poor. Contributing to the rigorous understanding of BP, in this paper we relate the convergence of BP to spectral properties of the graph. This encompasses a result for random graphs with a “planted” solution; thus, we obtain the first rigorous result on BP for graph coloring in the case of a complex graphical structure (as opposed to trees). In particular, the analysis shows how Belief Propagation breaks the symmetry between the 3! possible permutations of the color classes.
منابع مشابه
Palette-colouring: a belief-propagation approach
We consider a variation of the prototype combinatorial-optimisation problem known as graph-colouring. Our optimisation goal is to colour the vertices of a graph with a fixed number of colours, in a way to maximise the number of different colours present in the set of nearest neighbours of each given vertex. This problem, which we pictorially call palette-colouring, has been recently addressed a...
متن کاملColouring random graphs and maximising local diversity
We study a variation of the graph colouring problem on random graphs of finite average connectivity. Given the number of colours, we aim to maximise the number of different colours at neighbouring vertices (i.e. one edge distance) of any vertex. Two efficient algorithms, belief propagation and Walksat are adapted to carry out this task. We present experimental results based on two types of rand...
متن کاملDependence-Conscious Global Register Allocation
Register allocation and instruction scheduling are antagonistic optimizations: Whichever is applied rst, it will impede the other. To solve this problem, we propose dependence-conscious colouring, a register allocation method that takes the dependence graph used by the instruction schedu-ler into consideration. Dependence-conscious colouring consists of two parts: First, the interference graph ...
متن کاملBelief Propagation and Spectral Methods Belief Propagation and Spectral Methods
We investigate an algorithm derived based on the belief propagation method of Pearl [11] applied to the (Min-)Bisection problem under the standard planted solution model (or more precisely the Most Likely Partition problem under the same planted solution model). We first point out that the algorithm (without thresholding) is nothing but the standard power method for computing an eigenvector wit...
متن کاملHyperspectral image unmixing via bilinear generalized approximate message passing
In hyperspectral unmixing, the objective is to decompose an electromagnetic spectral dataset measured over M spectral bands and T pixels, into N constituent material spectra (or “endmembers”) with corresponding spatial abundances. In this paper, we propose a novel approach to hyperspectral unmixing (i.e., joint estimation of endmembers and abundances) based on loopy belief propagation. In parti...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Combinatorics, Probability & Computing
دوره 18 شماره
صفحات -
تاریخ انتشار 2009