Turnitin
降AI改写
早检测系统
早降重系统
Turnitin-UK版
万方检测-期刊版
维普编辑部版
Grammarly检测
Paperpass检测
checkpass检测
PaperYY检测
[HTML][HTML] λ-Deformation: A Canonical Framework for Statistical Manifolds of Constant Curvature
J Zhang, TKL Wong - Entropy, 2022 - mdpi.com
This paper systematically presents the λ-deformation as the canonical framework of
deformation to the dually flat (Hessian) geometry, which has been well established in …
deformation to the dually flat (Hessian) geometry, which has been well established in …
Tsallis and Rényi deformations linked via a new λ-duality
Tsallis and Rényi entropies, which are monotone transformations of each other, are
deformations of the celebrated Shannon entropy. Maximization of these deformed entropies …
deformations of the celebrated Shannon entropy. Maximization of these deformed entropies …
Hierarchy of deformations in concavity
K Ishige, P Salani, A Takatsu - Information Geometry, 2024 - Springer
A deformation is a positive continuous function defined on an appropriate interval. Through
deformations, we generalize the notion of concavity for functions. We introduce the order …
deformations, we generalize the notion of concavity for functions. We introduce the order …
Pseudo-Riemannian geometry encodes information geometry in optimal transport
Optimal transport and information geometry both study geometric structures on spaces of
probability distributions. Optimal transport characterizes the cost-minimizing movement from …
probability distributions. Optimal transport characterizes the cost-minimizing movement from …
Legendre duality: from thermodynamics to information geometry
J Naudts, J Zhang - Information Geometry, 2024 - Springer
This paper reviews the role of convex duality in Information Geometry. It clarifies the notion
of bi-orthogonal coordinates associated with Legendre duality by treating its two underlying …
of bi-orthogonal coordinates associated with Legendre duality by treating its two underlying …
Generalization of the maximum entropy principle for curved statistical manifolds
The maximum entropy principle (MEP) is one of the most prominent methods to investigate
and model complex systems. Despite its popularity, the standard form of the MEP can only …
and model complex systems. Despite its popularity, the standard form of the MEP can only …
Thermodynamics of exponential Kolmogorov–Nagumo averages
This paper investigates generalized thermodynamic relationships in physical systems where
relevant macroscopic variables are determined by the exponential Kolmogorov–Nagumo …
relevant macroscopic variables are determined by the exponential Kolmogorov–Nagumo …
Conformal mirror descent with logarithmic divergences
The logarithmic divergence is an extension of the Bregman divergence motivated by optimal
transport and a generalized convex duality, and satisfies many remarkable properties. Using …
transport and a generalized convex duality, and satisfies many remarkable properties. Using …
λ-Deformed probability families with subtractive and divisive normalizations
J Zhang, TKL Wong - Handbook of Statistics, 2021 - Elsevier
This chapter investigates deformations to the exponential family and the mixture family of
probability density functions, under both subtractive and divisive normalizations. We study …
probability density functions, under both subtractive and divisive normalizations. We study …
A certain ODE-system defining the geometric divergence
T Kurose - Information Geometry, 2024 - Springer
A system of ordinary differential equations satisfied by the geometric divergence, a
generalization of the canonical divergence on a dually flat space, is introduced. By using the …
generalization of the canonical divergence on a dually flat space, is introduced. By using the …