Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:1111.0490 · Modern Physics Letters B

DATA SET MODELS AND EXPONENTIAL FAMILIES IN STATISTICAL PHYSICS AND BEYOND

Jan Naudts, Ben Anthonis

Published Mar 23, 2012• 7 citations
arXivHTMLPDF

Abstract

The exponential family of models is defined in a general setting, not relying on probability theory. Some results of information geometry are shown to remain valid. Exponential families both of classical and of quantum mechanical statistical physics fit into the new formalism. Other less obvious applications are predicted. For instance, quantum states can be modeled as points in a classical phase space and the resulting model belongs to the exponential family.

DOI
10.1142/s0217984912500625

Related papers

Analysis of generalized Gibbs states

Stephan Weis, Ilya M. Spitkovsky

An exponential family is a manifold of generalized Gibbs state of the form exp(H)/Tr(exp(H)), where H belongs to a vector space of (possibly non-commutative) hermitian matrices. Generalized Gibbs states are important in small-scale thermodynamics, they represent equilibrium states regarding several conserved quantities that admit novel operations without heat dissipation [1]. Quantum information theory and condensed matter physics consider a space of local Hamiltonians acting on spins. The entropy distance from this exponential family is a measure of many-body complexity [2,3,4]. This talk is concerned with the geometry and topology of an exponential family and its entropy distance [5]. The maximum-entropy inference map parametrizes the exponential family. This map is continuous in the interior of its domain, the joint numerical range [6]. We describe the points of discontinuity in terms of open mapping theorems and eigenvalue crossings. Because of the discontinuity, the inference map and the entropy distance cannot be approximated through interior points. Instead, it is necessary to study faces (flat portions on the boundary) of the joint numerical range. With local Hamiltonians, this requires studying the faces of the set of quantum marginals. References. [1] M. Lostaglio, D. Jennings, and T. Rudolph,New Journal of Physics 19, 043008 (2017). [2] N. Ay, E. Olbrich, N. Bertschinger, and J. Jost,Chaos 21, 037103 (2011). [3] S. Niekamp, T. Galla, M. Kleinmann, and O. Gühne, J. Phys. A-Math. Gen. 46, 125301 (2013). [4] B. Zeng, X. Chen, D.-L. Zhou, and X.-G. Wen, Quantum Information Meets Quantum Matter,New York: Springer, 2019. [5] S. Weis, Journal of Convex Analysis 21, 339-399 (2014). [6] L. Rodman, I. M. Spitkovsky, A. Szkoła, and S. Weis,Journal of Mathematical Physics 57, 015204 (2016).

Proceedings of Entropy 2021: The Scientific Tool of the 21st Century•May 5, 2021•0 citations

Exponential Families with Incompatible Statistics and Their Entropy Distance

Stephan Weis

This work generalizes the interaction measure of multi-information known in probability theory to finite-level quantum systems.This is done in the more general context of the entropy distance from an exponential family.One of the most well-known measures of stochastic dependence is multi-information, applied in various fields including Neuroscience and Statistical Mechanics.Multi-information is the entropy distance from an exponential family.In statistics, an exponential family is a very familiar parametric model, it admits a simple geometric description of entropy distance and maximum-likelihood estimation by mean values.But a complete description of these concepts requires to study extensions of a family, an investigation that was started by N. N. Čencov and O. Barndorff-Nielsen and continued principally by I. Csiszár and F. Matúš.Very little is known about extensions of an exponential family for a finite-level quantum system.In this thesis we consider mean value parameters of the statistic of such a family and a suitable extension thereof.Generalizing probability theory, we prove that the parameters describe the entropy distance from the family and they parametrize its rIclosure consisting of the points approximated in relative entropy.The dimension function of a local maximizer of entropy distance is bounded by the dimension of the family.We show that the rI -closure of a Gibbs family consists of the maximum entropy ensembles.A new and generic phenomenon of a non-abelian exponential family is the appearance of non-exposed faces of the convex mean value set.We prove that mean values of the closure of an e-geodesic included in the family meet only the relative interior of exposed faces.Unlike in finite probability spaces there are examples with a discontinuous entropy distance, the continuity being equivalent to equality of rI -closure and topological closure of the family.Examples suggest that the topology of an exponential family is related to the topology of associated projector lattices and to open projections and symmetrizations of state spaces.We conclude that multi-information for a quantum system is a continuous function equal to the entropy distance from a factorizable family.For analysis of a factorizable family we supply a partial classification of convex exponential families.As a perspective to a dynamical situation we examine a measure of temporal interaction for abelian systems, which is related to multi-information.i Being able to write this thesis in the Mathematical Physics group at Friedrich-Alexander-Universität Erlangen-Nürnberg was a great opportunity.In the first place I want to thank my supervisor Prof. Andreas Knauf for the constant and friendly support in conversations about ideas and literature both in mathematics and physics and for his encouragement to a systematic problem solving.

•Jan 1, 2010•7 citations

Mean-field equations for higher-order quantum statistical models : an information geometric approach

Nihal Yapage

This work is a simple extension of \cite{NNjpa}. We apply the concepts of information geometry to study the mean-field approximation for a general class of quantum statistical models namely the higher-order quantum Boltzmann machines (QBMs). The states we consider are assumed to have at most third-order interactions with deterministic coupling coefficients. Such states, taken together, can be shown to form a quantum exponential family and thus can be viewed as a smooth manifold. In our work, we explicitly obtain naive mean-field equations for the third-order classical and quantum Boltzmann machines and demonstrate how some information geometrical concepts, particularly, exponential and mixture projections used to study the naive mean-field approximation in \cite{NNjpa} can be extended to a more general case. Though our results do not differ much from those in \cite{NNjpa}, we emphasize the validity and the importance of information geometrical point of view for higher dimensional classical and quantum statistical models.

arXiv:1202.5726•Feb 26, 2012•0 citations

Quantum Statistical Mechanics in Classical Phase Space

Phil Attard

Quantum and classical results are often presented as being dependent upon separate postulates as if the two are distinct and unrelated, and there is little attempt to show how the quantum implies the classical. The transformation to classical phase space gives researchers access to a range of algorithms derived from classical statistical mechanics that promise results on much more favourable numerical terms. Quantum Statistical Mechanics in Classical Phase Space offers not just a new computational approach to condensed matter systems, but also a unique conceptual framework for understanding the quantum world and collective molecular behaviour. A formally exact transformation, this revolutionary approach goes beyond the quantum perturbation of classical condensed matter to applications that lie deep in the quantum regime. It offers scalable computational algorithms and tractable approximations tailored to specific systems. Concrete examples serve to validate the general approach and demonstrate new insights. For example, the computer simulations and analysis of the λ-transition in liquid helium provide a new molecular-level explanation of Bose–Einstein condensation and a quantitative theory for superfluid flow. The intriguing classical phase space formulation in this book offers students and researchers a range of new computational algorithms and analytic approaches. It offers not just an efficient computational approach to quantum condensed matter systems, but also an exciting perspective on how the classical world that we observe emerges from the quantum mechanics that govern the behaviour of atoms and molecules. The applications, examples, and physical insights foreshadow new discoveries in quantum condensed matter systems. Key features • A computationally efficient approach to quantum condensed-matter many-particle systems based on a formally exact transformation of quantum statistical mechanics to classical phase space. • Shows how the observed classical world emerges from the underlying quantum mechanics of atoms and molecules. • Describes successive quantum corrections to classical statistical mechanics. • Derives a number of expansions that account for the non-commutativity of quantum position and momentum operators when transformed to classical phase space. • Tests various computer simulation algorithms against benchmark results for model condensed matter systems.

Institute of Physics eBooks•Nov 1, 2021•0 citations

The Quantum Mechanical Formalism Derived from the Probabilistic Nature of Quantitative Physical Predictions

Hans Rudolf Tschudi

It is a scientific truism nowadays that quantum mechanical predictions are of statistical or rather of probabilistic nature: a quantum theory assigns a probability distribution to each measurable quantity (observable) of a physical system prepared according to a given preparation prescription (state). Such sets of probability distributions represent the most general quantitative predictions of physical theories. The aim of this study is to determine all theoretical frameworks which yield such a kind of output taking the probabilistic nature of quantitative physical predictions as initial hypothesis. Astonishingly, this project succeeds with a minimal number of additional assumptions, which arise quite naturally in the course of the analysis, and which essentially amount to regularity conditions. The result is that there exist only two classes of physical theories providing quantitative probabilistic predictions: classical theories where observables are represented by real functions over a phase space and states are represented by probability measures upon the phase space, and quantum theories where observables are represented by selfadjoint operators acting on a complex Hilbert space and states are represented by state operators. On empirical grounds, classical theories cannot provide the all-encompassing, fundamental frame for the mathematical description of physical systems. Quantum theories remain, and there is no more complete formal frame for quantitative physical theories. As an additional result, it is shown that there exist physical systems which possess a quantum mechanical but no classical description; a prominent example is the spin system of two spin-1/2 particles. The classical hidden variables model, which J. Bell relates to this system in order to prove his theorem, cannot be a true description of it because no such classical model exists, and Bell's theorem loses its foundation.

•Mar 5, 2026•0 citations

On quantum information manifolds

Anna Jenčová

The aim of information geometry is to introduce a suitable geometrical structure on families of probability distributions or quantum states. For parametrised statistical models, such structure is based on two fundamental notions: the Fisher information and the exponential family with its dual mixed parametrisation, see for example (Amari 1985, Amari and Nagaoka 2000).

Cambridge University Press eBooks•Oct 22, 2009•3 citations
The exponential family of models is defined in a general setting, not relying on probability theory. Some results of information geometry are shown to remain valid. Exponential families both of classical and of quantum mechanical statistical physics fit into the new formalism. Other less obvious applications are predicted. For instance, quantum states can be modeled as points in a classical phase space and the resulting model belongs to the exponential family.
An exponential family is a manifold of generalized Gibbs state of the form exp(H)/Tr(exp(H)), where H belongs to a vector space of (possibly non-commutative) hermitian matrices. Generalized Gibbs states are important in small-scale thermodynamics, they represent equilibrium states regarding several conserved quantities that admit novel operations without heat dissipation [1]. Quantum information theory and condensed matter physics consider a space of local Hamiltonians acting on spins. The entropy distance from this exponential family is a measure of many-body complexity [2,3,4]. This talk is concerned with the geometry and topology of an exponential family and its entropy distance [5]. The maximum-entropy inference map parametrizes the exponential family. This map is continuous in the interior of its domain, the joint numerical range [6]. We describe the points of discontinuity in terms of open mapping theorems and eigenvalue crossings. Because of the discontinuity, the inference map and the entropy distance cannot be approximated through interior points. Instead, it is necessary to study faces (flat portions on the boundary) of the joint numerical range. With local Hamiltonians, this requires studying the faces of the set of quantum marginals. References. [1] M. Lostaglio, D. Jennings, and T. Rudolph,New Journal of Physics 19, 043008 (2017). [2] N. Ay, E. Olbrich, N. Bertschinger, and J. Jost,Chaos 21, 037103 (2011). [3] S. Niekamp, T. Galla, M. Kleinmann, and O. Gühne, J. Phys. A-Math. Gen. 46, 125301 (2013). [4] B. Zeng, X. Chen, D.-L. Zhou, and X.-G. Wen, Quantum Information Meets Quantum Matter,New York: Springer, 2019. [5] S. Weis, Journal of Convex Analysis 21, 339-399 (2014). [6] L. Rodman, I. M. Spitkovsky, A. Szkoła, and S. Weis,Journal of Mathematical Physics 57, 015204 (2016).
This work generalizes the interaction measure of multi-information known in probability theory to finite-level quantum systems.This is done in the more general context of the entropy distance from an exponential family.One of the most well-known measures of stochastic dependence is multi-information, applied in various fields including Neuroscience and Statistical Mechanics.Multi-information is the entropy distance from an exponential family.In statistics, an exponential family is a very familiar parametric model, it admits a simple geometric description of entropy distance and maximum-likelihood estimation by mean values.But a complete description of these concepts requires to study extensions of a family, an investigation that was started by N. N. Čencov and O. Barndorff-Nielsen and continued principally by I. Csiszár and F. Matúš.Very little is known about extensions of an exponential family for a finite-level quantum system.In this thesis we consider mean value parameters of the statistic of such a family and a suitable extension thereof.Generalizing probability theory, we prove that the parameters describe the entropy distance from the family and they parametrize its rIclosure consisting of the points approximated in relative entropy.The dimension function of a local maximizer of entropy distance is bounded by the dimension of the family.We show that the rI -closure of a Gibbs family consists of the maximum entropy ensembles.A new and generic phenomenon of a non-abelian exponential family is the appearance of non-exposed faces of the convex mean value set.We prove that mean values of the closure of an e-geodesic included in the family meet only the relative interior of exposed faces.Unlike in finite probability spaces there are examples with a discontinuous entropy distance, the continuity being equivalent to equality of rI -closure and topological closure of the family.Examples suggest that the topology of an exponential family is related to the topology of associated projector lattices and to open projections and symmetrizations of state spaces.We conclude that multi-information for a quantum system is a continuous function equal to the entropy distance from a factorizable family.For analysis of a factorizable family we supply a partial classification of convex exponential families.As a perspective to a dynamical situation we examine a measure of temporal interaction for abelian systems, which is related to multi-information.i Being able to write this thesis in the Mathematical Physics group at Friedrich-Alexander-Universität Erlangen-Nürnberg was a great opportunity.In the first place I want to thank my supervisor Prof. Andreas Knauf for the constant and friendly support in conversations about ideas and literature both in mathematics and physics and for his encouragement to a systematic problem solving.
This work is a simple extension of \cite{NNjpa}. We apply the concepts of information geometry to study the mean-field approximation for a general class of quantum statistical models namely the higher-order quantum Boltzmann machines (QBMs). The states we consider are assumed to have at most third-order interactions with deterministic coupling coefficients. Such states, taken together, can be shown to form a quantum exponential family and thus can be viewed as a smooth manifold. In our work, we explicitly obtain naive mean-field equations for the third-order classical and quantum Boltzmann machines and demonstrate how some information geometrical concepts, particularly, exponential and mixture projections used to study the naive mean-field approximation in \cite{NNjpa} can be extended to a more general case. Though our results do not differ much from those in \cite{NNjpa}, we emphasize the validity and the importance of information geometrical point of view for higher dimensional classical and quantum statistical models.
Quantum and classical results are often presented as being dependent upon separate postulates as if the two are distinct and unrelated, and there is little attempt to show how the quantum implies the classical. The transformation to classical phase space gives researchers access to a range of algorithms derived from classical statistical mechanics that promise results on much more favourable numerical terms. Quantum Statistical Mechanics in Classical Phase Space offers not just a new computational approach to condensed matter systems, but also a unique conceptual framework for understanding the quantum world and collective molecular behaviour. A formally exact transformation, this revolutionary approach goes beyond the quantum perturbation of classical condensed matter to applications that lie deep in the quantum regime. It offers scalable computational algorithms and tractable approximations tailored to specific systems. Concrete examples serve to validate the general approach and demonstrate new insights. For example, the computer simulations and analysis of the λ-transition in liquid helium provide a new molecular-level explanation of Bose–Einstein condensation and a quantitative theory for superfluid flow. The intriguing classical phase space formulation in this book offers students and researchers a range of new computational algorithms and analytic approaches. It offers not just an efficient computational approach to quantum condensed matter systems, but also an exciting perspective on how the classical world that we observe emerges from the quantum mechanics that govern the behaviour of atoms and molecules. The applications, examples, and physical insights foreshadow new discoveries in quantum condensed matter systems. Key features • A computationally efficient approach to quantum condensed-matter many-particle systems based on a formally exact transformation of quantum statistical mechanics to classical phase space. • Shows how the observed classical world emerges from the underlying quantum mechanics of atoms and molecules. • Describes successive quantum corrections to classical statistical mechanics. • Derives a number of expansions that account for the non-commutativity of quantum position and momentum operators when transformed to classical phase space. • Tests various computer simulation algorithms against benchmark results for model condensed matter systems.
It is a scientific truism nowadays that quantum mechanical predictions are of statistical or rather of probabilistic nature: a quantum theory assigns a probability distribution to each measurable quantity (observable) of a physical system prepared according to a given preparation prescription (state). Such sets of probability distributions represent the most general quantitative predictions of physical theories. The aim of this study is to determine all theoretical frameworks which yield such a kind of output taking the probabilistic nature of quantitative physical predictions as initial hypothesis. Astonishingly, this project succeeds with a minimal number of additional assumptions, which arise quite naturally in the course of the analysis, and which essentially amount to regularity conditions. The result is that there exist only two classes of physical theories providing quantitative probabilistic predictions: classical theories where observables are represented by real functions over a phase space and states are represented by probability measures upon the phase space, and quantum theories where observables are represented by selfadjoint operators acting on a complex Hilbert space and states are represented by state operators. On empirical grounds, classical theories cannot provide the all-encompassing, fundamental frame for the mathematical description of physical systems. Quantum theories remain, and there is no more complete formal frame for quantitative physical theories. As an additional result, it is shown that there exist physical systems which possess a quantum mechanical but no classical description; a prominent example is the spin system of two spin-1/2 particles. The classical hidden variables model, which J. Bell relates to this system in order to prove his theorem, cannot be a true description of it because no such classical model exists, and Bell's theorem loses its foundation.