In this section
Several of our current PhD candidates and fellow researchers at the Data Science Institute have published, or in the proccess of publishing, papers to present their research.
@article{Rosas,
author = {Rosas, De Andraca FE and Morales, P},
journal = {Physical Review Research},
title = {A generalisation of the maximum entropy principle for curved statistical manifolds},
url = {http://hdl.handle.net/10044/1/91291},
}
TY - JOUR
AB - The maximum entropy principle (MEP) is one of the most prominent methods to investigate andmodel complex systems. Despite its popularity, the standard form of the MEP can only generateBoltzmann-Gibbs distributions, which are ill-suited for many scenarios of interest. As a principledapproach to extend the reach of the MEP, this paper revisits its foundations in information geometryand shows how the geometry of curved statistical manifolds naturally leads to a generalisation of theMEP based on the Rényi entropy. By establishing a bridge between non-Euclidean geometry andthe MEP, our proposal sets a solid foundation for the numerous applications of the Rényi entropy,and enables a range of novel methods for complex systems analysis.
AU - Rosas,De Andraca FE
AU - Morales,P
SN - 2643-1564
TI - A generalisation of the maximum entropy principle for curved statistical manifolds
T2 - Physical Review Research
UR - http://hdl.handle.net/10044/1/91291
ER -
Data Science Institute
William Penney Laboratory
Imperial College London
South Kensington Campus
London SW7 2AZ
United Kingdom
Email us.
Sign up to our mailing list.
Follow us on Twitter, LinkedIn and Instagram.
