Some Information Geometric Aspects of Cyber Security by Face Recognition

Secure user access to devices and datasets is widely enabled by fingerprint or face recognition. Organization of the necessarily large secure digital object datasets, with objects having content that may consist of images, text, video or audio, involves efficient classification and feature retrieval processing. This usually will require multidimensional methods applicable to data that is represented through a family of probability distributions. Then information geometry is an appropriate context in which to provide for such analytic work, whether with maximum likelihood fitted distributions or empirical frequency distributions. The important provision is of a natural geometric measure structure on families of probability distributions by representing them as Riemannian manifolds. Then the distributions are points lying in this geometrical manifold, different features can be identified and dissimilarities computed, so that neighbourhoods of objects nearby a given example object can be constructed. This can reveal clustering and projections onto smaller eigen-subspaces which can make comparisons easier to interpret. Geodesic distances can be used as a natural dissimilarity metric applied over data described by probability distributions. Exploring this property, we propose a new face recognition method which scores dissimilarities between face images by multiplying geodesic distance approximations between 3-variate RGB Gaussians representative of colour face images, and also obtaining joint probabilities. The experimental results show that this new method is more successful in recognition rates than published comparative state-of-the-art methods.     

Electrodynamics from a metric

A metric is given that produces a space in which the geodesic equation is identical with the Lorentz equation of motion for a charged particle. The gravitational field equations in the same space indicate a geometric origin for the electromagnetic energy-momentum tensor. A comparison is made with Kaluza-Klein theories and it is determined that the present theory is distinct from them because it corresponds to a timelike, noncompact fifth dimension. Since the metric is velocity-dependent, it is actually a Finsler space rather than a Riemannian space metric. Its special form, however, allows computations to be done in terms of Riemannian geometry.     

Methods of Information Geometry to model complex shapes

In this paper, a new statistical method to model patterns emerging in complex systems is proposed. A framework for shape analysis of 2? dimensional landmark data is introduced, in which each landmark is represented by a bivariate Gaussian distribution. From Information Geometry we know that Fisher-Rao metric endows the statistical manifold of parameters of a family of probability distributions with a Riemannian metric. Thus this approach allows to reconstruct the intermediate steps in the evolution between observed shapes by computing the geodesic, with respect to the Fisher-Rao metric, between the corresponding distributions. Furthermore, the geodesic path can be used for shape predictions. As application, we study the evolution of the rat skull shape. A future application in Ophthalmology is introduced.     

A Neural Network MCMC Sampler That Maximizes Proposal Entropy

Markov Chain Monte Carlo (MCMC) methods sample from unnormalized probability distributions and offer guarantees of exact sampling. However, in the continuous case, unfavorable geometry of the target distribution can greatly limit the efficiency of MCMC methods. Augmenting samplers with neural networks can potentially improve their efficiency. Previous neural network-based samplers were trained with objectives that either did not explicitly encourage exploration, or contained a term that encouraged exploration but only for well structured distributions. Here we propose to maximize proposal entropy for adapting the proposal to distributions of any shape. To optimize proposal entropy directly, we devised a neural network MCMC sampler that has a flexible and tractable proposal distribution. Specifically, our network architecture utilizes the gradient of the target distribution for generating proposals. Our model achieved significantly higher efficiency than previous neural network MCMC techniques in a variety of sampling tasks, sometimes by more than an order magnitude. Further, the sampler was demonstrated through the training of a convergent energy-based model of natural images. The adaptive sampler achieved unbiased sampling with significantly higher proposal entropy than a Langevin dynamics sample. The trained sampler also achieved better sample quality.     

The cornerstone role of the torsion in Finslerian physical worlds

It is shown that there are no metric-compatible connections with zero torsion onproperly Finslerian, i.e. post-Riemannian, metrics. Since Finslerian connections exist on Riemannian metrics, the torsion rather than the metric becomes the object which determines whether the geometry is properly Finslerian or not. On the other hand, the solder forms and connection are determined by the torsion if the affine curvature is zero, the torsion then containing all the information about the geometric reality of spacetime. Since the metric curvature may still be Riemannian, the question arises of whether its present central role in spacetime physics is but a consequence of requiring that all the geometric content of spacetime be contained in the metric.     

Einstein gravity in almost Kähler and Lagrange–Finsler variables and deformation quantization

A geometric procedure is elaborated for transforming (pseudo) Riemannian metrics and connections into canonical geometric objects (metric and nonlinear and linear connections) for effective Lagrange, or Finsler, geometries which, in turn, can be equivalently represented as almost Kähler spaces. This allows us to formulate an approach to quantum gravity following standard methods of deformation quantization. Such constructions are performed not on tangent bundles, as in usual Finsler geometry, but on spacetimes enabled with nonholonomic distributions defining 2+2$2+2$ splitting with associate nonlinear connection structure. We also show how the Einstein equations can be written in terms of Lagrange–Finsler variables and corresponding almost symplectic structures and encoded into the zero-degree cohomology coefficient for a quantum model of Einstein manifolds.     

Dislocations and internal length measurement in continuized crystals. I. Riemannian material space

Distributions of dislocations creating point defects are considered. These point defects are described by a metric tensor, which supplements a Burgers field responsible for dislocations. The metric tensor depends on the distribution of dislocations and defines a Riemannian geometry of the material space of a continuized crystal and thus an internal length measurement in this crystal. The dependence of the distribution of dislocations on the existence of point defects created by these dislocations is modeled by treating the Burgers field as a field defined on the Riemannian material space. Field equations, following from geometric identities, are formulated as balance equations on this Riemannian space and their source terms, responsible for interactions of dislocations and point defects, are identified.     

Information Geometry of the Exponential Family of Distributions with Progressive Type-II Censoring

In geometry and topology, a family of probability distributions can be analyzed as the points on a manifold, known as statistical manifold, with intrinsic coordinates corresponding to the parameters of the distribution. Consider the exponential family of distributions with progressive Type-II censoring as the manifold of a statistical model, we use the information geometry methods to investigate the geometric quantities such as the tangent space, the Fisher metric tensors, the affine connection and the α-connection of the manifold. As an application of the geometric quantities, the asymptotic expansions of the posterior density function and the posterior Bayesian predictive density function of the manifold are discussed. The results show that the asymptotic expansions are related to the coefficients of the α-connections and metric tensors, and the predictive density function is the estimated density function in an asymptotic sense. The main results are illustrated by considering the Rayleigh distribution.     

Kinematics of edge dislocations. I. Involutive distributions of local slip planes

The geometry of continuous distributions of dislocations and secondary point defects created by these distributions is considered. Particularly, the dependence of a distribution of dislocations on the existence of secondary point defects is modeled by treating dislocations as those located in a time-dependent Riemannian material space describing, in a continuous limit, the influence of these point defects on metric properties of a crystal structure. The notions of local glide systems and involutive distributions of local slip planes are introduced in order to describe, in terms of differential geometry, some aspects of the kinematics of the motion of edge dislocations. The analysis leads, among others, to the definition of a class of distributions of dislocations with a distinguished involutive distribution of local slip planes and such that a formula of mesoscale character describing the influence of edge dislocations on the mean curvature of glide surfaces is valid.     

Injectivity Radius of Lorentzian Manifolds

Motivated by the application to general relativity we study the geometry and regularity of Lorentzian manifolds under natural curvature and volume bounds, and we establish several injectivity radius estimates at a point or on the past null cone of a point. Our estimates are entirely local and geometric, and are formulated via a reference Riemannian metric that we canonically associate with a given observer (p, T) –where p is a point of the manifold and T is a future-oriented time-like unit vector prescribed at p only. The proofs are based on a generalization of arguments from Riemannian geometry. We first establish estimates on the reference Riemannian metric, and then express them in terms of the Lorentzian metric. In the context of general relativity, our estimate on the injectivity radius of an observer should be useful to investigate the regularity of spacetimes satisfying Einstein field equations.     

How can the neutrino interact with the electromagnetic field?

Maxwell electrodynamics in the fixed Minkowski space-time background can be described in an equivalent way in a curved Riemannian geometry that depends on the electromagnetic field and that we call the electromagnetic metric(e-metric for short). After showing such geometric equivalence we investigate the possibility that new processes dependent on the e-metric are allowed. In particular, for very high values of the field, a direct coupling of uncharged particles to the electromagnetic field may appear.     

Entropic Dynamics: Quantum Mechanics from Entropy and Information Geometry

Entropic Dynamics (ED) is a framework in which Quantum Mechanics (QM) is derived as an application of entropic methods of inference. The magnitude of the wave function is manifestly epistemic: its square is a probability distribution. The epistemic nature of the phase of the wave function is also clear: it controls the flow of probability. The dynamics is driven by entropy subject to constraints that capture the relevant physical information. The central concern is to identify those constraints and how they are updated. After reviewing previous work I describe how considerations from information geometry allow us to derive a phase space geometry that combines Riemannian, symplectic, and complex structures. The ED that preserves these structures is QM. The full equivalence between ED and QM is achieved by taking account of how gauge symmetry and charge quantization are intimately related to quantum phases and the single‐valuedness of wave functions.     

Deformation quantization of nonholonomic almost Kähler models and Einstein gravity

Nonholonomic distributions and adapted frame structures on (pseudo) Riemannian manifolds of even dimension are employed to build structures equivalent to almost Kähler geometry and which allows to perform a Fedosov-like quantization of gravity. The nonlinear connection formalism that was formally elaborated for Lagrange and Finsler geometry is implemented in classical and quantum Einstein gravity.     

Holomorphicity and the Walczak formula on Sasakian manifolds

The Walczak formula is a very nice tool for understanding the geometry of a Riemannian manifold equipped with two orthogonal complementary distributions. M. Svensson [Holomorphic foliations, harmonic morphisms and the Walczak formula, J. London Math. Soc. (2) 68 (3) (2003) 781–794] has shown that this formula simplifies to a Bochner-type formula when we are dealing with Kähler manifolds and holomorphic (integrable) distributions. We show in this paper that such results have a counterpart in Sasakian geometry. To this end, we build on a theory of (contact) holomorphicity on almost contact metric manifolds. Some other applications for (pseudo-)harmonic morphisms on Sasaki manifolds are outlined.     

Holomorphicity and the Walczak formula on Sasakian manifolds

The Walczak formula is a very nice tool for understanding the geometry of a Riemannian manifold equipped with two orthogonal complementary distributions. M. Svensson [Holomorphic foliations, harmonic morphisms and the Walczak formula, J. London Math. Soc. (2) 68 (3) (2003) 781–794] has shown that this formula simplifies to a Bochner-type formula when we are dealing with Kähler manifolds and holomorphic (integrable) distributions. We show in this paper that such results have a counterpart in Sasakian geometry. To this end, we build on a theory of (contact) holomorphicity on almost contact metric manifolds. Some other applications for (pseudo-)harmonic morphisms on Sasaki manifolds are outlined.     

Latent Network Construction for Univariate Time Series Based on Variational Auto-Encode

Time series analysis has been an important branch of information processing, and the conversion of time series into complex networks provides a new means to understand and analyze time series. In this work, using Variational Auto-Encode (VAE), we explored the construction of latent networks for univariate time series. We first trained the VAE to obtain the space of latent probability distributions of the time series and then decomposed the multivariate Gaussian distribution into multiple univariate Gaussian distributions. By measuring the distance between univariate Gaussian distributions on a statistical manifold, the latent network construction was finally achieved. The experimental results show that the latent network can effectively retain the original information of the time series and provide a new data structure for the downstream tasks.     

Matter Creation by Geometry in an Integrable Weyl-Dirac Theory

An integrable version of the Weyl-Dirac geometry is presented. This framework is a natural generalization of the Riemannian geometry, the latter being the basis of the classical general relativity theory. The integrable Weyl-Dirac theory is both coordinate covariant and gauge covariant (in the Weyl sense), and the field equations and conservation laws are derived from an action integral. In this framework matter creation by geometry is considered. It is found that a spatially confined, spherically symmetric formation made of pure geometric quantities is a massive entity. This may be treated either as a fundamental particle or as a cosmic body. In an F-R-W universe at the very beginning of the expansion phase the cosmic matter is created from an initial Planckian egg made of geometry, and during the following expansion geometric fields continue to stimulate the matter production.     

Entropic Dynamics on Gibbs Statistical Manifolds

Entropic dynamics is a framework in which the laws of dynamics are derived as an application of entropic methods of inference. Its successes include the derivation of quantum mechanics and quantum field theory from probabilistic principles. Here, we develop the entropic dynamics of a system, the state of which is described by a probability distribution. Thus, the dynamics unfolds on a statistical manifold that is automatically endowed by a metric structure provided by information geometry. The curvature of the manifold has a significant influence. We focus our dynamics on the statistical manifold of Gibbs distributions (also known as canonical distributions or the exponential family). The model includes an “entropic” notion of time that is tailored to the system under study; the system is its own clock. As one might expect that entropic time is intrinsically directional; there is a natural arrow of time that is led by entropic considerations. As illustrative examples, we discuss dynamics on a space of Gaussians and the discrete three-state system.