Worst-case bounds on the quality of max-product fixed-points
نویسندگان
چکیده
We study worst-case bounds on the quality of any fixed point assignment of the max-product algorithm for Markov Random Fields (MRF). We start providing a bound independent of the MRF structure and parameters. Afterwards, we show how this bound can be improved for MRFs with specific structures such as bipartite graphs or grids. Our results provide interesting insight into the behavior of max-product. For example, we prove that max-product provides very good results (at least 90% optimal) on MRFs with large variable-disjoint cycles1.
منابع مشابه
Tree consistency and bounds on the performance of the max-product algorithm and its generalizations
Finding the maximum a posteriori (MAP) assignment of a discrete-state distribution specified by a graphical model requires solving an integer program. The max-product algorithm, also known as the max-plus or min-sum algorithm, is an iterative method for (approximately) solving such a problem on graphs with cycles. We provide a novel perspective on the algorithm, which is based on the idea of re...
متن کاملOn Integral Operator and Argument Estimation of a Novel Subclass of Harmonic Univalent Functions
Abstract. In this paper we define and verify a subclass of harmonic univalent functions involving the argument of complex-value functions of the form f = h + ¯g and investigate some properties of this subclass e.g. necessary and sufficient coefficient bounds, extreme points, distortion bounds and Hadamard product.Abstract. In this paper we define and verify a subclass of harmonic univalent func...
متن کامل