Convex Optimization of Havrda-Charvat Distance (Divergence) Metric by Employing Lagrangian Policy in Intuitionistic Fuzzy Setting
Rohit Kumar Verma
Abstract

According to the established requirements, the distribution that minimizes the Kullback-Leibler divergence is chosen using the minimal likeliness distance (divergence) metric principle. This fundamental principle generalizes various approaches that have been put forth independently and cover a wide range of distributions. Additionally, we point out that the Lagrangian approach is a particular instance of minimum distance (divergence) metric (MDM) with a uniform posterior distribution. To provide much-needed clarification, this study is done in intuitionistic fuzzy environment thatgives us the analytical solutionand the direction which highlights this link.
Keywords: Aggregation, Lagrangian approach, distance (divergence) metric, Gamma Distribution, Thresholding, Optimization

PDF download