Natural gradient flow in the mixture geometry of a discrete exponential family
From MaRDI portal
Publication:296335
DOI10.3390/E17064215zbMATH Open1338.94030OpenAlexW1603321229MaRDI QIDQ296335FDOQ296335
Giovanni Pistone, Luigi Malagò
Publication date: 15 June 2016
Published in: Entropy (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.3390/e17064215
Cites Work
- On the geometry of discrete exponential families with application to exponential random graph models
- Title not available (Why is that?)
- On the toric algebra of graphical models
- Algebraic Statistics for Computational Biology
- The geometry of Hessian structures
- Lectures on curves, surfaces and projective varieties. A classical view of algebraic geometry. Transl. from the Italian by Francis Sullivan
- A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
- Title not available (Why is that?)
- Algebraic algorithms for sampling from conditional distributions
- Toric statistical models: parametric and binomial representations
- Combinatorial optimization with information geometry: the Newton method
- Generalised confounding with Grobner bases
- Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles
- Support sets in exponential families and oriented matroid theory
Cited In (6)
- Optimal transport natural gradient for statistical manifolds with continuous sample space
- Weyl geometric approach to the gradient-flow equations in information geometry
- Transport information Bregman divergences
- An eikonal equation approach to thermodynamics and the gradient flows in information geometry
- Hessian metric via transport information geometry
- Natural gradient via optimal transport
Uses Software
This page was built for publication: Natural gradient flow in the mixture geometry of a discrete exponential family
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q296335)
