We propose a new class of algorithms for minimizing or maximizing functions of parametric probabilistic models. These new algorithms are natural gradient algorithms that leverage more information than prior methods by using a new metric tensor in place of the commonly used Fisher information matrix. This new metric tensor is derived by computing directions of steepest ascent where the distance ...

The quantum Fisher information (QFI) plays a crucial role in theory and many practical applications such as metrology. However, computing the QFI is generally computationally demanding task. In this work we analyze lower bound on which call sub-quantum (sub-QFI). can be efficiently estimated computer for an n-qubit state using 2n qubits. sub-QFI based super-fidelity, upper Uhlmann's fidelity. W...

We have calculated the Tsallis entropy and Fisher information matrix (entropy) of spatially correlated nonextensive systems, by using an analytic non-Gaussian distribution obtained by the maximum entropy method. The effects of the correlated variability on the Fisher information matrix are shown to be different from those on the Tsallis entropy. The Fisher information is increased (decreased) b...

We consider three different approaches to define natural Riemannian metrics on polytopes of stochastic matrices. First, we define a natural class of stochastic maps between these polytopes and give a metric characterization of Chentsov type in terms of invariance with respect to these maps. Second, we consider the Fisher metric defined on arbitrary polytopes through their embeddings as exponent...

The subject of this paper is a mathematical transition from the Fisher information of classical statistics to the matrix formalism of quantum theory. If the monotonicity is the main requirement, then there are several quantum versions parametrized by a function. In physical applications the minimal is the most popular. There is a one-to-one correspondence between Fisher informations (called als...

Given a graph where vertices represent alternatives and pairwise comparison data, yij , is given on the edges, the statistical ranking problem is to find a potential function, defined on the vertices, such that the gradient of the potential function agrees with pairwise comparisons. We study the dependence of the statistical ranking problem on the available pairwise data, i.e., pairs (i, j) for...