2016 PKU Mini-Course: Information Geometry
This book is not yet featured on Listopia. Community Reviews. Showing Rating details. All Languages. More filters. Sort order. Mohammed rated it really liked it Jun 01, Jack Kamm rated it liked it Aug 28, Lucas rated it it was amazing Jan 09, Timothy rated it it was amazing Feb 18, Shaun Zhang rated it it was amazing Feb 19, Michael Redman rated it it was amazing Sep 08, Cryolite is currently reading it May 29, K added it Jun 10, John Taylor marked it as to-read May 30, Greg Linster marked it as to-read Mar 05, Nitin CR added it Mar 25, Cameron Smith marked it as to-read Feb 11, Alex marked it as to-read Oct 12, Arush Sarwar marked it as to-read Jan 28, Alok Singh marked it as to-read Apr 20, Skip to main content.
Subscribe to RSS
Advertisement Hide. Methods of Information Geometry to model complex shapes. Authors Authors and affiliations A. De Sanctis S. Part of the following topical collections: Mathematical Modeling of Complex Systems.
Methods of Information Geometry to model complex shapes | SpringerLink
This is a preview of subscription content, log in to check access. Amari, H. Nagaoka, Methods of Information Geometry , Vol.
Bertuglia, F. Bookstein, Stat.
About this book
Dryden, K. Classically, information geometry considered a parametrized statistical model as a Riemannian manifold.
- Information Geometry?
- HYBRID PHONONS IN NANOSTRUCTURES?
- Amari, Nagaoka - Methods of Information Geometry?
- Methods of Information Geometry - Shun-ichi Amari, Hiroshi Nagaoka - Google книги.
- Subscribe to RSS.
For such models, there is a natural choice of Riemannian metric, known as the Fisher information metric. In the special case that the statistical model is an exponential family , it is possible to induce the statistical manifold with a Hessian metric i.
In this case, the manifold naturally inherits two flat affine connections , as well as a canonical Bregman divergence. Historically, much of the work was devoted to studying the associated geometry of these examples.
In the modern setting, information geometry applies to a much wider context, including non-exponential families, nonparametric statistics , and even abstract statistical manifolds not induced from a known statistical model. The results combine techniques from information theory , affine differential geometry , convex analysis and many other fields. The history of information geometry is associated with the discoveries of at least the following people, and many others.
From Wikipedia, the free encyclopedia. This article may need to be rewritten to comply with Wikipedia's quality standards , as This should be edited to include some statistical background.. You can help.