Information Geometry
Издатель: Springer Nature · ISSN 2511-2481,2511-249X · 65 статей
- Fisher–Rao distances between finite-energy signals in Gaussian noise
-
GEORCE: a fast new control algorithm for computing geodesics
Abstract Computing geodesics for Riemannian manifolds is a difficult task that often relies on numerical approximations. However, these approximations tend to be either numerically unstable, have slow convergence, or scale poorly with...
-
Canonical foliations of statistical manifolds with statistical models
Abstract Constructing a realisation of a statistical manifold as a statistical model, i.e a manifold with dual connections with respect to a Fisher metric, is an important question in information geometry. While a positive answer to...
- EM algorithms for optimization problems with polynomial objectives
- Generalized convex nonnegative tensor decomposition on statistical manifolds
- A Commentary on Nagaoka-Amari 1982
- Differential geometry of smooth families of probability distributions
- Spectral rigidity and complexity from Fisher-entropy balance applications to open quantum systems
- Families of costs with zero and nonnegative MTW tensor in optimal transport and the c-divergences
- Geodesic connectedness on statistical manifolds with cubic forms divisible by the metric
- Statistical biharmonicity of identity maps
- Minimum copula divergence for robust estimation
- Half a century of information geometry, part 2
- Information Geometry of Variational Bayes
- Deep learning generalization and the convex hull of training sets
- Information geometry of Gaussian processes and its applications to transfer learning
- Efficiency of maximum likelihood estimation for a multinomial distribution with known probability sums
-
Singularities in bivariate normal mixtures
Abstract We investigate mappings whose components are bivariate normal densities from the perspective of singularity theory. Motivated by the need to understand two-component bivariate normal mixtures, we classify these mappings up to...
-
Quasi-symmetry and geometric marginal homogeneity: a simplicial approach to square contingency tables
Abstract Square contingency tables are traditionally analyzed with a focus on the symmetric structure of the corresponding probability tables. We view probability tables as elements of a simplex equipped with the Aitchison geometry....
-
On the attainment of the Wasserstein–Cramer–Rao lower bound
Abstract Recently, a Wasserstein analogue of the Cramer–Rao inequality has been developed using the Wasserstein information matrix (Otto metric). This inequality provides a lower bound on the Wasserstein variance of an estimator, which...
- Homogeneous statistical manifolds
- An explicit formula for Hessian potentials on warped product manifolds
- Exponential families and affine Grassmannians
-
Approximation of the measured Kullback–Leibler divergence as a generalized chi-squared random variable
Abstract The Kullback–Leibler (KL) divergence between a pair of parameterized probability distributions becomes a random variable when the parameters are equipped with a prior distribution. In the case of exponential family...
-
Shrinkage priors for circulant correlation structure models
Abstract We consider a new statistical model called the circulant correlation structure model, which is a multivariate Gaussian model with unknown covariance matrix and has a scale-invariance property. We construct shrinkage priors for...
- Non degeneracy of affinelike lie algebra
-
A geometric modeling of Occam’s razor in deep learning
Abstract Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs . stunning performance in practice is all the more intriguing and not explainable using the standard...
- Maximum information divergence from linear and toric models
-
Dual stochastic natural gradient descent
Abstract The multinomial logistic regression (MLR) model is widely used in statistics and machine learning. On the one hand, stochastic gradient descent (SGD) is the most common approach for determining the parameters of a such model in...
-
Generalized estimation and information
Abstract This paper extends the idea of a generalized estimator for a scalar parameter (Vos in Inform Geom 7:151–170, 2022) to multi-dimensional parameters both with and without nuisance parameters. The title reflects the fact that...