Natural gradient flow in the mixture geometry of a discrete exponential family

DOI10.3390/e17064215zbMath1338.94030OpenAlexW1603321229MaRDI QIDQ296335

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

Mathematics Subject Classification ID

Information theory (general) (94A15)

Related Items (6)

Weyl geometric approach to the gradient-flow equations in information geometry ⋮ Natural gradient via optimal transport ⋮ Optimal transport natural gradient for statistical manifolds with continuous sample space ⋮ Transport information Bregman divergences ⋮ An eikonal equation approach to thermodynamics and the gradient flows in information geometry ⋮ Hessian metric via transport information geometry

Uses Software

• CoCoA
• 4ti2

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Combinatorial optimization with information geometry: the Newton method
• Support sets in exponential families and oriented matroid theory
• Lectures on curves, surfaces and projective varieties. A classical view of algebraic geometry. Transl. from the Italian by Francis Sullivan
• Algebraic algorithms for sampling from conditional distributions
• A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
• On the geometry of discrete exponential families with application to exponential random graph models
• Toric statistical models: parametric and binomial representations
• On the toric algebra of graphical models
• Generalised confounding with Grobner bases
• Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles
• Algebraic Statistics for Computational Biology

This page was built for publication: Natural gradient flow in the mixture geometry of a discrete exponential family