Information Geometry Article Index for
Information
Website Links For
Information
 

Information About

Information Geometry





INTRODUCTION


The main tenet of information geometry is that many important structures in Probability Theory , Information Theory and Statistics can be treated as structures in Differential Geometry by regarding a Space Of Probabilities as a Differential Manifold endowed with a Riemannian Metric and a family of Affine Connection s. For example,

The importance of studying statistical structures as geometrical structures lies in the fact that geometric structures are invariant under coordinate transforms. For example, a family of probability distributions, such as Gaussian distributions, may be transformed into another family of distributions, such as log-normal distributions, by a change of variables. However, the fact of it being an exponential family is not changed, since the latter is a geometric property. The distance between two distributions in this family defined through Fisher metric will also be preserved.

The great statistician Fisher recognized in the 1920s that there is an intrinsic measure of amount of information for statistical estimators. The Fisher information matrix was shown by Cramer and Rao to be a Riemannian metric on the space of probabilities, and became known as Fisher information metric.

The mathematician Cencov (Chentsov) proved in the 1960s and 1970s that on the space of probability distributions on a sample space containing at least three points,
  • There exists a unique intrinsic metric. It is the Fisher information metric.

  • There exists a unique one parameter family of affine connections. It is the family of \alpha-affine connections later popularized by Amari.

  • Both of these uniqueness are, of course, up to the multiplication by a constant.


Amari's study in the 1980s brought all these results together, with the introduction of the concept of Dual-affine Connection s, and the interplay among Metric , Affine Connection and Divergence(information Geometry) . In particular,
  • Given a Riemannian metric ''g'' and a family of dual affine connections \Gamma_\alpha, there exists a unique set of dual divergences D_\alpha defined by them.

  • Given the family of dual divergences D_\alpha, the metric and affine connections can be uniquely determined by second order and third order differentiations.



BASIC CONCEPTS


  • Statistical manifold: space of probability distribution, statistical model.

  • Point on the manifold: probability distribution.

  • Coordinates: parameters in the statistical model.

  • Tangent vector: Fisher score function.

  • Riemannian metric: Fisher information metric.

  • Affine connections.

  • Curvatures: associated with information loss

  • Information divergence.



FISHER INFORMATION METRIC AS A RIEMANNIAN METRIC


Information geometry is based primarily on the Fisher Information Metric :

:g_{ij}=\int rac{\partial \log p(x, heta)}{\partial heta_i} rac{\partial \log p(x, heta)}{\partial heta_j} p(x, heta)\, dx

Substituting ''i'' = −log(''p'') from Information Theory , the formula becomes:

:g_{ij}=\int rac{\partial i(x, heta)}{\partial heta_i} rac{\partial i(x, heta)}{\partial heta_j} p(x, heta)\, dx

Which can be thought of intuitively as: "The distance between two points on a statistical differential manifold is the amount of information between them, i.e. the informational difference between them."

Thus, if a point in information space represents the state of a system, then the trajectory of that point will, on average, be a Random Walk through information space, i.e. will Diffuse according to Brownian Motion .

With this in mind, the information space can be thought of as a Fitness Landscape , a trajectory through this space being an "evolution". The Brownian motion of evolution trajectories thus represents the No Free Lunch phenomena discussed by Stuart Kauffman .


HISTORY


The history of information is associated with the discoveries of at least the following people, and many others


SOME APPLICATIONS



Natural gradient

An important concept in information geometry is the Natural Gradient . The concept and theory of the natural gradient suggests an adjustment to the Energy Function of a Learning Rule . This adjustment takes into account the Curvature of the (prior) Statistical Differential Manifold , by way of the Fisher information metric.

This concept has many important applications in Blind Signal Separation , Neural Network s, Artificial Intelligence , and other engineering problems that deal with information. Experimental results have shown that application of the concept leads to substantial performance gains.


REFERENCES

  • Shun'ichi Amari - ''Differential-geometrical methods in statistics'', Lecture notes in statistics, Springer-Verlag, Berlin, 1985

  • Shun'ichi Amari, Hiroshi Nagaoka - ''Methods of information geometry'', Transactions of mathematical monographs; v. 191, American Mathematical Society, 2000

  • M. Murray and J. Rice - ''Differential geometry and statistics'', Monographs on Statistics and Applied Probability 48, Chapman and Hall, 1993.

  • R. E. Kass and P. W. Vos - ''Geometrical Foundations of Asymptotic Inference'', Series in Probability and Statistics, Wiley, 1997.