Highly Influenced

5 Excerpts

@article{Zhang2013NonparametricIG, title={Nonparametric Information Geometry: From Divergence Function to Referential-Representational Biduality on Statistical Manifolds}, author={Jing Zhang}, journal={Entropy}, year={2013}, volume={15}, pages={5384-5418} }

- Published in Entropy 2013
DOI:10.3390/e15125384

Divergence functions are the non-symmetric “distance” on the manifold,Mθ, of parametric probability density functions over a measure space, (X,μ). Classical information geometry prescribes, on Mθ: (i) a Riemannian metric given by the Fisher information; (ii) a pair of dual connections (giving rise to the family of α-connections) that preserve the metric under parallel transport by their joint actions; and (iii) a family of divergence functions (α-divergence) defined on Mθ × Mθ, which induce the… CONTINUE READING

SHOWING 1-10 OF 70 REFERENCES

Highly Influential

8 Excerpts

Highly Influential

4 Excerpts

Highly Influential

6 Excerpts

Highly Influential

6 Excerpts

Highly Influential

3 Excerpts

Highly Influential

3 Excerpts

Highly Influential

9 Excerpts

Highly Influential

17 Excerpts

Highly Influential

9 Excerpts

Highly Influential

13 Excerpts

Loading similar papers…