boostingdivergencedually flat manifoldsdually flat structureinformation geometryinvariant information geometrymanifolds of probability distributionstatistical inference
Three-dimensional polytopes (52B10) Introductory exposition (textbooks, tutorial papers, etc.) pertaining to differential geometry (53-01) Linear and affine connections (53B05) Introductory exposition (textbooks, tutorial papers, etc.) pertaining to statistics (62-01) Statistical aspects of information-theoretic topics (62B10) Characterization and structure theory of statistical distributions (62E10) Asymptotic properties of parametric estimators (62F12) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05) Introductory exposition (textbooks, tutorial papers, etc.) pertaining to information and communication theory (94-01) Information theory (general) (94A15) Measures of information, entropy (94A17)
The book is an introduction to information geometry and its applications. We learn from the preface of this book that the term ``information geometry refers to a way of exploring the world of information by means of geometry. This field emerged from the study of the invariant geometrical structures inherent in statistical inference. Technically speaking, one has a Riemannian metric together with dually coupled affine connections in a manifold of probability distributions. The fields of applications of information geometry include, besides statistical inference, mathematics, physics, neurosciences and several areas of information sciences, like machine learning processing and optimization. The book is divided into 4 parts. In part I begins with the definition of a divergence between two points of a manifold. This is measure of the degree of separation between the two points. This leads to the notion of dually coupled asymmetry, and from here to the dual world. The manifold is then equipped with a dually flat structure equipped with a Riemannian metric. A generalized Pythagorean theorem in a dually flat information manifold is given. The dually flat structure is a special case of a Riemannian geometry equipped with non-flat dual affine connections, studied in Part II. Part II is a gentle introduction to dual differential geometry. On Part III the author addresses the field of statistical inference and he presents various ideas and results on this subject. Part IV is an overview of applications of information geometry in several fields, including machine learning and signal processing. The author starts with a question of pattern recognition, namely, obtaining a representative of a cluster of patterns, called the center of the cluster. Another question addressed is that of dividing a non-labeled aggregate of patterns into a set of clusters. In the case where the patterns are generated randomly subject to a probability distribution depending on each class, stochastic versions of the above problems is addressed. Information geometry deals with these problems in terms of divergence. The book is original and interesting.
- The relation between information theory and the differential geometry approach to statistics
- Information geometry and statistical manifold.
- Geometry of the \(q\)-exponential distribution with dependent competing risks and accelerated life testing
- On statistical properties of Jizba-Arimitsu hybrid entropy
- An information geometric perspective on the complexity of macroscopic predictions arising from incomplete information
- Geometric structures of information. Proceedings of the conference on geometric science of information, GSI 2017
- Bayesian duality and risk analysis on the statistical manifold of exponential family with censored data
- A pedagogical intrinsic approach to relative entropies as potential functions of quantum metrics: The \(q\)-\(z\) family
- Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
- Logarithmic divergences from optimal transport and Rényi geometry
- Wasserstein Riemannian geometry of Gaussian densities
- Natural gradient via optimal transport
- Statistical structures in almost paracontact geometry
- Embedding optimal transports in statistical manifolds
- Exponentially concave functions and a new information geometry
- On the convergence time of a natural dynamics for linear programming
- Fisher-Rao geometry of Dirichlet distributions
- Optimal transport natural gradient for statistical manifolds with continuous sample space
- Cramér-Rao lower bounds arising from generalized Csiszár divergences
- Ricci curvature for parametric statistics via optimal transport
- Geometric theory of information. Selected and revised contributions of the first conference on the geometric sciences of information, GSI, Paris, France, August 2013
- Elliptic isometries of the manifold of positive definite real matrices with the trace metric
- Natural gradient for combined loss using wavelets
- \(\alpha\)-connections in generalized geometry
- Confounding ghost channels and causality: a new approach to causal information flows
- Special Vinberg cones
- Natural alpha embeddings
- The dually flat structure for singular models
- Towards a canonical divergence within information geometry
- Subsystem complexity after a global quantum quench
- Pairwise rigid registration based on Riemannian geometry and Lie structures of orientation tensors
- Accelerated information gradient flow
- Bayesian regression and classification using Gaussian process priors indexed by probability density functions
- Emergent quantumness in neural networks
- Nonequilibrium in thermodynamic formalism: the second law, gases and information geometry
- Self-similar solutions to the Hesse flow
- Transport information Bregman divergences
- Structured ambiguity and model misspecification
- An eikonal equation approach to thermodynamics and the gradient flows in information geometry
- Information geometry for Fermi-Dirac and Bose-Einstein quantum statistics
- Geodesic in-betweenness for means of several matrices
- The \(q\)-exponentials do not maximize the Rényi entropy
- Regression using localised functional Bregman divergence
- Wasserstein statistics in one-dimensional location scale models
- On a prior based on the Wasserstein information matrix
- Local normal forms of EM-wavefronts in affine flat coordinates
- Entropic dynamics yields reciprocal relations
- Information geometry and Hamiltonian systems on Lie groups
- Harmonicity of conformally-projectively equivalent statistical manifolds and conformal statistical submersions
- Projections with logarithmic divergences
- Wasserstein statistics in one-dimensional location-scale models
- Wasserstein proximal of GANs
- Computing statistical divergences with sigma points
- Transport information Hessian distances
- The geodesic distance on the generalized gamma manifold for texture image retrieval
- Geometry and control of thermodynamic systems described by generalized exponential families
- On the canonical distributions of a thermal particle in a generalized velocity-dependent potential
- Universality classes for the Fisher metric derived from relative group entropy
- A shape distance based on the Fisher-Rao metric and its application for shapes clustering
- Monoparametric family of metrics derived from classical Jensen-Shannon divergence
- Information geometry of operator scaling
- Information geometry on the curved \(q\)-exponential family with application to survival data analysis
- Exponential arcs in the manifold of vector states on a -finite von Neumann algebra
- Optimal transportation plans with escort entropy regularization
- Pseudo-Riemannian geometry encodes information geometry in optimal transport
- Entropy-regularized 2-Wasserstein distance between Gaussian measures
- Computational mean-field information dynamics associated with reaction-diffusion equations
- Geometry on degradation models and mis-specification analysis by using \(\alpha\)-divergence
- Information geometry of physics-informed statistical manifolds and its use in data assimilation
- On some information geometric structures concerning mercator projections
- A projection pricing model for non-Gaussian financial returns
- Reparametrizations and metric structures in thermodynamic phase space
- Divergences on symmetric cones and medians
- Probabilistic programming with stochastic variational message passing
- Towards understanding sparse filtering: a theoretical perspective
- Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics
- Quantum Hellinger distances revisited
- The Kähler geometry of certain optimal transport problems
- Mini-batch learning of exponential family finite mixture models
- The geometric structure on a degradation model with application to optimal design under a cost constraint
- Multiplicative Schrödinger problem and the Dirichlet transport
- Mirror descent algorithms for minimizing interacting free energy
- A concurrence theorem for alpha-connections on the space of t-distributions and its application
- Geometry of the probability simplex and its connection to the maximum entropy method
- A divergence center interpretation of general symmetric Kubo-Ando means, and related weighted multivariate operator means
- Quantum divergences with p-power means
- Appearance of thermal time
- Amari-Chentsov structure on the statistical manifold of models for accelerated life tests
- Book review of: N. Ay et al., Information geometry
- The geometry of recombination
- On the geometry of Bayesian inference
- Kantorovich problems and conditional measures depending on a parameter
- Estimation of a continuous distribution on the real line by discretization methods
- Geometry on the statistical manifold induced by the degradation model with soft failure data
- Matrix versions of the Hellinger distance
- Hessian transport gradient flows
- Information geometry and sufficient statistics
- On geodesic completeness for Riemannian metrics on smooth probability densities
- Dynamical aspects in the quantizer-dequantizer formalism
- Information geometry and game theory
This page was built for publication: Information geometry and its applications
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q908098)
