English
Related papers

Related papers: Some minimization problems for the free analogue o…

200 papers

We extend Voiculescu's microstates-free definitions of free Fisher information and free entropy to the non-tracial framework. We explain the connection between these quantities and free entropy with respect to certain completely positive…

Operator Algebras · Mathematics 2007-05-23 Dimitri Shlyakhtenko

The Fisher information approximation (FIA) is an implementation of the minimum description length principle for model selection. Unlike information criteria such as AIC or BIC, it has the advantage of taking the functional form of a model…

Methodology · Statistics 2018-08-02 Daniel W. Heck , Morten Moshagen , Edgar Erdfelder

We prove two lower bounds for the complexity of non-log-concave sampling within the framework of Balasubramanian et al. (2022), who introduced the use of Fisher information (FI) bounds as a notion of approximate first-order stationarity in…

Machine Learning · Statistics 2022-10-07 Sinho Chewi , Patrik Gerber , Holden Lee , Chen Lu

Through the study of large deviations theory for matrix Brownian motion, Biane-Capitaine-Guionnet proved the inequality $\chi(X) \leq \chi^*(X)$ that relates two analogs of entropy in free probability defined by Voiculescu. We give a new…

Operator Algebras · Mathematics 2024-04-03 David Jekel , Jennifer Pi

We consider kinetic models for Fermi-Dirac-like particles obeying the exclusion principle. A generalized notion of Fisher information, tailored to kinetic equations of Fermi-Dirac-Fokker-Planck type, is introduced via the associated entropy…

Analysis of PDEs · Mathematics 2025-08-22 Yuzhe Zhu

The principle of minimum Fisher information states that in the set of acceptable probability distributions characterizing the given system, it is best done by the one that minimizes the corresponding Fisher information. This principle can…

General Finance · Quantitative Finance 2022-03-24 Marcin Makowski , Edward W. Piotrowski , Piotr Frąckiewicz , Marek Szopa

A non-commutative non-selfadjoint random variable z is called R-diagonal, if its *-distribution is invariant under multiplication by free unitaries: if a unitary w is *-free from z, then the *-distribution of z is the same as that of wz.…

Operator Algebras · Mathematics 2007-05-23 A. Nica , D. Shlyakhtenko , R. Speicher

We propose the generalised Fisher information or the one-parameter extended class of the Fisher information for the case of one random variable. This new form of the Fisher information is obtained from the intriguing connection between the…

Statistics Theory · Mathematics 2022-08-25 Worachet Bukaew , Sikarin Yoo-Kong

Motivated by the information bound for the asymptotic variance of M-estimates for scale, we define Fisher information of scale of any distribution function F on the real line as a suitable supremum. In addition, we enforce equivariance by a…

Statistics Theory · Mathematics 2015-03-17 Peter Ruckdeschel , Helmut Rieder

This paper considers the problem of estimation of the Fisher information for location from a random sample of size $n$. First, an estimator proposed by Bhattacharya is revisited and improved convergence rates are derived. Second, a new…

Information Theory · Computer Science 2020-05-08 Wei Cao , Alex Dytso , Michael Fauß , H. Vincent Poor , Gang Feng

Fisher's information measure plays a very important role in diverse areas of theoretical physics. The associated measures as functionals of quantum probability distributions defined in, respectively, coordinate and momentum spaces, are the…

Quantum Physics · Physics 2015-04-20 Angelo Plastino , Guido Bellomo , Angel R. Plastino

We prove lower bounds on the error of any estimator for the mean of a real probability distribution under the knowledge that the distribution belongs to a given set. We apply these lower bounds both to parametric and nonparametric…

Statistics Theory · Mathematics 2024-03-05 Rémy Degenne , Timothée Mathieu

We define and study a relative free entropy quantity, analogous in its properties to Voiculescu's relative free entropy Chi^*(...:B). Our definition uses matricial microstates, unlike his definition, which involves non-commutative Hilbert…

Operator Algebras · Mathematics 2007-05-23 Dimitri Shlyakhtenko

We examine important properties of the difference between the variance and the quantum Fisher information over four, i.e., $(\Delta A)^2-F_{\rm Q}[\varrho,A]/4.$ We find that it is equal to a generalized variance defined in Petz [J. Phys. A…

Quantum Physics · Physics 2018-08-22 Geza Toth

We propose a modified $\chi^{\beta}$-divergence, give some of its properties, and show that this leads to the definition of a generalized Fisher information. We give generalized Cram\'er-Rao inequalities, involving this Fisher information,…

Information Theory · Computer Science 2013-05-28 Jean-François Bercher

We consider the Landau-Coulomb equation for initial data with bounded mass, finite numbers of moments, and entropy. We show the existence of a global weak solution that has bounded Fisher information for positive times. This solution is…

Analysis of PDEs · Mathematics 2024-10-15 Laurent Desvillettes , William Golding , Maria Pia Gualdani , Amelie Loher

The notion of a $*$-law or $*$-distribution in free probability is also known as the quantifier-free type in Farah, Hart, and Sherman's model theoretic framework for tracial von Neumann algebras. However, the full type can also be…

Operator Algebras · Mathematics 2022-08-31 David Jekel

We present in this work variants of existing estimates for the Landau or Landau-Fermi-Dirac entropy dissipation, in terms of Fisher information, in the hard potential case. The specificity of those variants is that the entropy is never used…

Analysis of PDEs · Mathematics 2024-01-08 Laurent Desvillettes

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…

Quantum Physics · Physics 2017-08-23 Denes Petz , Catalin Ghinea

We consider the problem of learning high-dimensional, nonparametric and structured (e.g. Gaussian) distributions in distributed networks, where each node in the network observes an independent sample from the underlying distribution and can…

Information Theory · Computer Science 2019-06-04 Leighton Pate Barnes , Yanjun Han , Ayfer Ozgur
‹ Prev 1 2 3 10 Next ›