Locally Conformally Hessian and Statistical Manifolds [PDF]
A statistical manifold $\left(M,D,g\right)$ is a manifold $M$ endowed with a torsion-free connection $D$ and a Riemannian metric $g$ such that the tensor $D g$ is totally symmetric. If $D$ is flat then $\left(M,g,D\right)$ is a Hessian manifold. A locally conformally Hessian (l.c.H) manifold is a quotient of a Hessian manifold $(C,\nabla,g)$ such that ...
Pavel Osipov
exaly +6 more sources
Hessian Regularization Based Factorization Algorithm Combining Multi-view and Non-negative Matrix [PDF]
Non-negative matrix does not consider the manifold of data when represents multi-view data,which results in the ineffective express of the data internal expression.In this paper,Hessian regularized Non-negative Matrix Factorization(NMF) is proposed.By ...
WANG Chaofeng,SHI Jun,WU Jinjie,ZHU Jie
doaj +2 more sources
A Note on Pseudo-Umbilical Submanifolds of Hessian Manifolds with Constant Hessian Sectional Curvature [PDF]
The geometry of Hessian manifold, as a branch of statistics, physics, Kaehlerian, and affine differential geometry, is deeply fruitful and a new field for scientists. However, inspite of its importance submanifolds and curvature conditions of it have not been so well known yet.
Yilmaz, Münevver Yildirim +1 more
openaire +4 more sources
Hessian Based Smoothing Splines for Manifold Learning
20 ...
Kim, Juno
openaire +4 more sources
Relative-Entropy Variational Principle for Semiclassical Gravity with Finite-Resolution Boundaries [PDF]
This work formulates semiclassical gravity within a causal-diamond framework where a finite-resolution boundary provides the edge structure for a local Wheeler–DeWitt description.
Olivier Nusbaumer
doaj +2 more sources
Generalized Legendre Transforms Have Roots in Information Geometry [PDF]
Artstein-Avidan and Milman [Annals of mathematics (2009), (169):661–674] characterized invertible reverse-ordering transforms in the space of lower, semi-continuous, extended, real-valued convex functions as affine deformations of the ordinary Legendre ...
Frank Nielsen
doaj +2 more sources
An Approach to Fisher-Rao Metric for Infinite Dimensional Non-Parametric Information Geometry [PDF]
Non-parametric information geometry has long faced an “intractability barrier”: in the infinite-dimensional setting, the Fisher–Rao metric is a weak Riemannian metric functional that lacks a bounded inverse, rendering classical optimization and ...
Bing Cheng, Howell Tong
doaj +2 more sources
The Pontryagin Forms of Hessian Manifolds [PDF]
We show that Hessian manifolds of dimensions 4 and above must have vanishing Pontryagin forms. This gives a topological obstruction to the existence of Hessian metrics. We find an additional explicit curvature identity for Hessian 4-manifolds. By contrast, we show that all analytic Riemannian 2-manifolds are Hessian.
John Armstrong, Shun-ichi Amari
openaire +3 more sources
Hessian-regularized co-training for social activity recognition. [PDF]
Co-training is a major multi-view learning paradigm that alternately trains two classifiers on two distinct views and maximizes the mutual agreement on the two-view unlabeled data.
Weifeng Liu +4 more
doaj +1 more source
Bismut-Stroock Hessian formulas and local Hessian estimates for heat semigroups and harmonic functions on Riemannian manifolds [PDF]
peer reviewedIn this article, we develop a martingale approach to localized Bismut-type Hessian formulas for heat semigroups on Riemannian manifolds. Our approach extends the Hessian formulas established by Stroock (1996) and removes in particular the ...
Cheng, Li-Juan +5 more
core +1 more source

