Information Geometry
Издатель: Springer Nature · ISSN 2511-2481,2511-249X · 65 статей
- Preface to the special issue on further developments of information geometry (FDIG2025)
- Preface to the special issue on geometric science of information (GSI’25)
- Information geometry of perturbed gradient flow systems on hypergraphs: a perspective towards nonequilibrium physics
- ODE for entropic optimal transport: interpolating between Kullback–Leibler and Wasserstein geometries
-
Bioinspired CNNs for border completion in occluded images
Abstract We exploit the mathematical modeling of the border completion problem in the visual cortex to design convolutional neural network (CNN) filters that enhance robustness to image occlusions. We evaluate our CNN architecture,...
- Fields of covariances on non-commutative probability spaces in finite dimensions
- Autoparallelity of quantum statistical manifolds in light of quantum estimation theory
- Equivariant log-extrinsic statistics on symmetric cones
- Wasserstein projection estimators for circular distributions
-
A Born structure on the tangent bundle of a Hessian manifold
Abstract The Hessian structure is a geometric structure consisting of a pair $$(\nabla ,g)$$ ( ∇ , g ) of an affine connection $$\nabla $$ ∇ and a Riemannian metric g satisfying certain compatibility conditions. In information geometry,...
- Robust inference using density-powered Stein operators
- Weak adversarial networks for solving 2D incompressible Navier–Stokes-Brinkman equations
- Structural properties of entropic vectors and stability of the Ingleton inequality
-
Modeling the structure of high-dimensional data using a multivariate Bernoulli distribution
Abstract Recent experiments have uncovered that several high-dimensional datasets have a high probability of forming binary clusters after projecting the data on a randomly chosen one-dimensional subspace. This paper presents a...
- Unique Fisher–Shannon balance points on spheres and flat tori
-
Semi-simple isometries of the manifold of symmetric positive definite real matrices with the trace metric
Abstract We study the semi-simple (or non-parabolic) isometries $$\Phi $$ Φ of the manifold $$\mathcal {P}_n$$ P n of symmetric positive definite real matrices, endowed with the trace metric g and pay attention to the set $$Min(\Phi )$$...
-
Nonlinear dimensionality reduction through optimal transport between incomparable spaces
Abstract We study a dimensionality reduction method grounded in optimal transport theory, leveraging the Gromov–Wasserstein (GW) distance to align the relational geometry of data across incomparable spaces. Building on recent advances...
- Improving Cramér–Rao bound and its variants: an extrinsic geometry perspective
-
A dyadic path construction as a geometric realization of the 1-Wasserstein distance on the simplex
Abstract The standard n -simplex $$\Delta ^n$$ Δ n serves as a natural geometric space for representing discrete probability distributions and compositional data. Quantifying dissimilarity between points $$P, Q \in \Delta ^n$$ P , Q ∈ Δ...
- Foundations of quantum local asymptotic normality via information geometry
-
A companion to the Nagaoka–Amari structure on the denormalized state space
Abstract This paper investigates Markov-invariant geometric structures on the denormalized state space, the space of strictly positive measures on a finite set. Within the subclass of structures compatible with the classical...
-
Flatness of location-scale-shape models under the Wasserstein metric
Abstract In Wasserstein geometry, one-dimensional location–scale models are flat both intrinsically and extrinsically—that is, they are curvature-free as well as totally geodesic in the space of probability distributions. In this study,...
- A general framework for divergence approximation on Gaussian mixture models
- Transport alpha divergences
-
Information geometry of absorbing Markov-chain and discriminative random walks
Abstract Discriminative Random Walks (DRWs) are a simple yet powerful tool for semi-supervised node classification, but their theoretical foundations remain fragmentary. We revisit DRWs through the lens of information geometry, treating...
-
Classification of scaling and translation invariant exponential families on the real line
Abstract The family of normal distributions on $$\mathbb {R}$$ R is closed under scaling and translation. Another example of an exponential family on $$\mathbb {R}$$ R with this property is the family of exponential-polynomial...
-
The moduli spaces of left-invariant statistical structures on Lie groups
Abstract In the context of information geometry, the concept known as left-invariant statistical structure on Lie groups is defined by Furuhata–Inoguchi–Kobayashi (Inf Geom 4(1):177–188, 2021). In this paper, we introduce the notion of...
-
Nonexistence of dual measures of the NEF-GHS
Abstract This paper studies the inverse problem in information geometry: given a Hessian manifold, is it derived from an open exponential family? As a motivating case, we prove that for the natural exponential family generated by the...
-
Characterization of exponential families of lumpable stochastic matrices
Abstract It is known that the set of lumpable Markov chains over a finite state space, with respect to a fixed lumping function, generally does not form an exponential family of stochastic matrices. In this work, we explore efficiently...
- Metric-dependent transients in non-Markovian relaxation: Kullback–Leibler vs entropic optimal transport