A Novel Approach to Canonical Divergences within Information Geometry

نویسندگان

  • Nihat Ay
  • Shun-ichi Amari
چکیده

A divergence function defines a Riemannian metric g and dually coupled affine connections ∇ and ∇∗ with respect to it in a manifold M . When M is dually flat, that is flat with respect to ∇ and ∇∗, a canonical divergence is known, which is uniquely determined from (M, g,∇,∇∗). We propose a natural definition of a canonical divergence for a general, not necessarily flat, M by using the geodesic integration of the inverse exponential map. The new definition of a canonical divergence reduces to the known canonical divergence in the case of dual flatness. Finally, we show that the integrability of the inverse exponential map implies the geodesic projection property.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Discrete Singular Convolution Method for the Seepage Analysis in Porous Media with Irregular Geometry

A novel discrete singular convolution (DSC)  formulation  is  presented for the seepage analysis in irregular geometric porous media. The DSC is a new promising numerical approach which has been recently applied to solve several engineering problems. For a medium with regular geometry, realizing of the DSC for the seepage analysis is straight forward. But DSC implementation for a medium with ir...

متن کامل

Design of a Novel Framework to Control Nonlinear Affine Systems Based on Fast Terminal Sliding-Mode Controller

In this paper, a novel approach for finite-time stabilization of uncertain affine systems is proposed. In the proposed approach, a fast terminal sliding mode (FTSM) controller is designed, based on the input-output feedback linearization of the nonlinear system with considering its internal dynamics. One of the main advantages of the proposed approach is that only the outputs and external state...

متن کامل

A Geometry Preserving Kernel over Riemannian Manifolds

Abstract- Kernel trick and projection to tangent spaces are two choices for linearizing the data points lying on Riemannian manifolds. These approaches are used to provide the prerequisites for applying standard machine learning methods on Riemannian manifolds. Classical kernels implicitly project data to high dimensional feature space without considering the intrinsic geometry of data points. ...

متن کامل

Escort entropies and divergences and related canonical distribution

We discuss two families of two-parameter entropies and divergences, derived from the standard Rényi and Tsallis entropies and divergences. These divergences and entropies are found as divergences or entropies of escort distributions. Exploiting the nonnegativity of the divergences, we derive the expression of the canonical distribution associated to the new entropies and a observable given as a...

متن کامل

مطالعه تئوری و آزمایشگاهی جهش هیدرولیکی واگرا در مقاطع ذوزنقه‌ای شکل

خTo reduce the construction costs of stilling basins of hydraulic jump type is sometimes, novel geometries are sometimes used to adopt the basin to the upstream and downstream sections without any transition structures. Otherwise, any changes in the geometry of the basin would cause changes in the conditions and characteristics of the hydraulic jump. In this study, the effects of variation in b...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Entropy

دوره 17  شماره 

صفحات  -

تاریخ انتشار 2015