A new model selection criterion based on information geometry

Abstract

This paper presents a new model selection criterion based on information geometry - Information Geometric Model Selection Criterion (IGMSC) which is reparametrization invariant, and gives the proof. IGMSC computes the geometric complexity of the model by regarding the model space as the manifold and estimates the model-data geometric fitness by using the divergence between the true distribution and the asymptotic distribution, enduing complexity and fitness with clear geometric significance. IGMSC gives the theoretic support of model selection in the framework of information geometry.