Data set models and exponential families in statistical physics and beyond
From MaRDI portal
Publication:4918261
DOI10.1142/S0217984912500625zbMATH Open1262.82003arXiv1111.0490MaRDI QIDQ4918261FDOQ4918261
Authors: Jan Naudts, Ben Anthonis
Publication date: 24 April 2013
Published in: Modern Physics Letters B (Search for Journal in Brave)
Abstract: The exponential family of models is defined in a general setting, not relying on probability theory. Some results of information geometry are shown to remain valid. Exponential families both of classical and of quantum mechanical statistical physics fit into the new formalism. Other less obvious applications are predicted. For instance, quantum states can be modeled as points in a classical phase space and the resulting model belongs to the exponential family.
Full work available at URL: https://arxiv.org/abs/1111.0490
Recommendations
Cites Work
- Title not available (Why is that?)
- Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems
- Possible generalization of Boltzmann-Gibbs statistics.
- Information Theory and Statistical Mechanics
- Title not available (Why is that?)
- Quantum information theory and quantum statistics.
- Generalised Thermostatistics
- Introduction to Nonextensive Statistical Mechanics
- Title not available (Why is that?)
- Information geometry of \(q\)-Gaussian densities and behaviors of solutions to related diffusion equations
- Geometry of \(q\)-exponential family of probability distributions
- Generalised exponential families and associated entropy functions
- Geometric study for the Legendre duality of generalized entropies and its application to the porous medium equation
- Bregman divergence as relative operator entropy
- Game theoretical optimization inspired by information theory
Cited In (4)
This page was built for publication: Data set models and exponential families in statistical physics and beyond
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4918261)