On Em Algorithms and Their Proximal Generalizations
نویسندگان
چکیده
In this paper, we analyze the celebrated EM algorithm from the point of view of proximal point algorithms. More precisely, we study a new type of generalization of the EM procedure introduced in [Chretien and Hero (1998)] and called Kullback-proximal algorithms. The proximal framework allows us to prove new results concerning the cluster points. An essential contribution is a detailed analysis of the case where some cluster points lie on the boundary of the parameter space. Mathematics Subject Classification. 65C20, 65C60. Received June 14, 2007. Revised June 27, 2007.
منابع مشابه
A Mathematical Optimization Model for Solving Minimum Ordering Problem with Constraint Analysis and some Generalizations
In this paper, a mathematical method is proposed to formulate a generalized ordering problem. This model is formed as a linear optimization model in which some variables are binary. The constraints of the problem have been analyzed with the emphasis on the assessment of their importance in the formulation. On the one hand, these constraints enforce conditions on an arbitrary subgraph and then g...
متن کاملAn Optimization Model for Epidemic Mitigation and Some Theoretical and Applied Generalizations
In this paper, we present a binary-linear optimization model to prevent the spread of an infectious disease in a community. The model is based on the remotion of some connections in a contact network in order to separate infected nodes from the others. By using this model we nd an exact optimal solution and determine not only the minimum number of deleted links but also their exact positions. T...
متن کاملEM algorithms without missing data.
Most problems in computational statistics involve optimization of an objective function such as a loglikelihood, a sum of squares, or a log posterior function. The EM algorithm is one of the most effective algorithms for maximization because it iteratively transfers maximization from a complex function to a simple, surrogate function. This theoretical perspective clarifies the operation of the ...
متن کاملOrdered Weighted Averaging Operators and their Generalizations with Applications in Decision Making
The definition of ordered weighted averaging (OWA) operators and their applications in decision making are reviewed. Also, some generalizations of OWA operators are studied and then, the notion of 2-symmetric OWA operators is introduced. These generalizations are illustrated by some examples.
متن کاملGeneralizations of the Skew t-Normal Distribution and their Properties
In this paper we consider several generalizations of the skew t-normal distribution, and some of their properties. Also, we represent several theorems for constructing each generalized skew t-normal distribution. Next, we illustrate the application of the proposed distribution studying the ratio of two heavy metals, Nickel and Vanadium, associated with crude oil in Shadgan wetland in the south-...
متن کامل