English
Related papers

Related papers: An approximate quantum Cram\'{e}r--Rao bound based…

200 papers

We investigate the connection between the time-evolution of averages of stochastic quantities and the Fisher information and its induced statistical length. As a consequence of the Cramer-Rao bound, we find that the rate of change of the…

Statistical Mechanics · Physics 2020-07-01 Sosuke Ito , Andreas Dechant

Quantum Fisher information matrix (QFIM) is a core concept in theoretical quantum metrology due to the significant importance of quantum Cram\'{e}r-Rao bound in quantum parameter estimation. However, studies in recent years have revealed…

Quantum Physics · Physics 2020-03-27 Jing Liu , Haidong Yuan , Xiao-Ming Lu , Xiaoguang Wang

A deep neural network is a hierarchical nonlinear model transforming input signals to output signals. Its input-output relation is considered to be stochastic, being described for a given input by a parameterized conditional probability…

Machine Learning · Computer Science 2018-08-23 Shun-ichi Amari , Ryo Karakida , Masafumi Oizumi

The Fisher-Rao distance between two probability distributions of a statistical model is defined as the Riemannian geodesic distance induced by the Fisher information metric. In order to calculate the Fisher-Rao distance in closed-form, we…

Information Theory · Computer Science 2025-01-08 Frank Nielsen

This paper derives lower bounds for the mean square errors of parameter estimators in the case of Poisson distributed data subjected to multiple abrupt changes. Since both change locations (discrete parameters) and parameters of the Poisson…

Information Theory · Computer Science 2016-10-31 Lucien Bacharach , Mohammed Nabil El Korso , Alexandre Renaux , Jean-Yves Tourneret

In the present paper, we would like to draw attention to a possible generalized Fisher information that fits well in the formalism of nonextensive thermostatistics. This generalized Fisher information is defined for densities on…

Mathematical Physics · Physics 2013-01-18 J. -F. Bercher

We present several inequalities related to the Robertson-Schr\"odinger uncertainty relation. In all these inequalities, we consider a decomposition of the density matrix into a mixture of states, and use the fact that the…

Quantum Physics · Physics 2024-01-23 Géza Tóth , Florian Fröwis

Mimicking the maximum likelihood estimator, we construct first order Cramer-Rao efficient and explicitly computable estimators for the scale parameter $\sigma^2$ in the model $Z_{i,n}=\sigma n^{-\beta}X_i+Y_i,i=1,\ldots,n,\beta>0$ with…

Statistics Theory · Mathematics 2015-03-20 Till Sabel , Johannes Schmidt-Hieber

The problem of side-information scalable (SI-scalable) source coding is considered in this work, where the encoder constructs a progressive description, such that the receiver with high quality side information will be able to truncate the…

Information Theory · Computer Science 2007-08-01 Chao Tian , Suhas N. Diggavi

Uncertainty relations (URs) like the Heisenberg-Robertson or the time-energy UR are often considered to be hallmarks of quantum theory. Here, a simple derivation of these URs is presented based on a single classical inequality from…

Quantum Physics · Physics 2015-09-14 Florian Fröwis , Roman Schmied , Nicolas Gisin

A lower bound is an important tool for predicting the performance that an estimator can achieve under a particular statistical model. Bayesian bounds are a kind of such bounds which not only utilizes the observation statistics but also…

Statistics Theory · Mathematics 2023-03-02 Shuo Tang , Gerald LaMountain , Tales Imbiriba , Pau Closas

We shall give a new Schr\"odinger type uncertainty relation for a quantity representing a quantum uncertainty, introduced by S.Luo in \cite{Luo1}. Our result improves the Heisenberg uncertainty relation shown in \cite{Luo1} for a mixed…

Quantum Physics · Physics 2015-05-19 Shigeru Furuichi

Multipartite quantum entanglement, as a core quantum resource, is fundamental to the advancement of quantum science and technology. In multipartite quantum systems, there are two kinds of quantum entanglement: $k$-nonseparability and…

Quantum Physics · Physics 2025-10-27 Xiaofei Qi , Yuyang Pang , Jinchuan Hou

It is a specific type of quantum correlated state that achieves optimal precision in parameterestimation under unitary encoding. We consider the potential experimental limitation on probe entanglement, and find a relation between achievable…

Quantum Physics · Physics 2026-01-06 Debarupa Saha , Ujjwal Sen

An uncertainty relation for the R\'enyi entropies of conjugate quantum observables is used to obtain a strong Heisenberg limit of the form ${\rm RMSE} \geq f(\alpha)/(\langle N\rangle+\frac12)$, bounding the root mean square error of any…

Quantum Physics · Physics 2022-11-21 Michael J. W. Hall

This paper gives an overview about particular quasi-entropies, generalized quantum covariances, quantum Fisher informations, skew-informations and their relations. The point is the dependence on operator monotone functions. It is proven…

Functional Analysis · Mathematics 2007-12-19 Denes Petz , V. E. Sandor Szabo

We address the fundamental limits of learning unknown parameters of any stochastic process from time-series data, and discover exact closed-form expressions for how optimal inference scales with observation length. Given a parametrized…

Machine Learning · Computer Science 2023-10-09 Paul M. Riechers

We present a new proof of the quantum Cramer-Rao bound for precision parameter estimation [1-3] and extend it to a more general class of measurement procedures. We analyze a generalized framework for parameter estimation that covers most…

Quantum Physics · Physics 2010-01-28 Garry Goldstein , Mikhail D. Lukin , Paola Cappellaro

We introduce a refinement to the convex split lemma by replacing the max mutual information with the collision mutual information, transforming the inequality into an equality. This refinement yields tighter achievability bounds for quantum…

Quantum Physics · Physics 2025-02-18 Gilad Gour

Communication efficient distributed mean estimation is an important primitive that arises in many distributed learning and optimization scenarios such as federated learning. Without any probabilistic assumptions on the underlying data, we…

Information Theory · Computer Science 2022-11-15 Prathamesh Mayekar , Shubham Jha , Ananda Theertha Suresh , Himanshu Tyagi