Bayesian generalized probability calculus for density matrices

DOI10.1007/S10994-009-5133-7MaRDI QIDQ1959541zbMATH OpenOpenAlexFDO

Authors Manfred K. Warmuth, Dima Kuzmin

Publication date 7 October 2010

Published in Machine Learning (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial 4.0 International

Full work available at URL https://arxiv.org/abs/0901.1273

zbMATH Keywords

density matrixgeneralized probabilityprobability calculusquantum Bayes rule

Mathematics Subject Classification ID

Axioms; other general questions in probability (60A05) Foundations of probability theory (60A99) Bayesian problems; characterization of Bayes procedures (62C10) Bayesian inference (62F15) Quantum state spaces, operational and probabilistic concepts (81P16)

Abstract: One of the main concepts in quantum physics is a density matrix, which is a symmetric positive definite matrix of trace one. Finite probability distributions can be seen as a special case when the density matrix is restricted to be diagonal. We develop a probability calculus based on these more general distributions that includes definitions of joints, conditionals and formulas that relate these, including analogs of the Theorem of Total Probability and various Bayes rules for the calculation of posterior density matrices. The resulting calculus parallels the familiar "conventional" probability calculus and always retains the latter as a special case when all matrices are diagonal. We motivate both the conventional and the generalized Bayes rule with a minimum relative entropy principle, where the Kullbach-Leibler version gives the conventional Bayes rule and Umegaki's quantum relative entropy the new Bayes rule for density matrices. Whereas the conventional Bayesian methods maintain uncertainty about which model has the highest data likelihood, the generalization maintains uncertainty about which unit direction has the largest variance. Surprisingly the bounds also generalize: as in the conventional setting we upper bound the negative log likelihood of the data by the negative log likelihood of the MAP estimator.

Recommendations

• Quantum theory of Jaynes' principle, Bayes' theorem, and information
• scientific article; zbMATH DE number 1098886
• Picturing classical and quantum Bayesian inference
• Bayesian analog of Gleason’s theorem
• Schrödinger equations with van der Waals type potentials

Cites work

• Exponentiated gradient versus gradient descent for linear predictors
• Gleason-type derivations of the quantum probability rule for generalized measurements
• scientific article; zbMATH DE number 1579275 (Why is no real title available?)
• scientific article; zbMATH DE number 5957285 (Why is no real title available?)
• scientific article; zbMATH DE number 3128586 (Why is no real title available?)
• scientific article; zbMATH DE number 3676222 (Why is no real title available?)
• scientific article; zbMATH DE number 3721567 (Why is no real title available?)
• scientific article; zbMATH DE number 1234233 (Why is no real title available?)
• scientific article; zbMATH DE number 2161246 (Why is no real title available?)
• scientific article; zbMATH DE number 967931 (Why is no real title available?)
• Online Variance Minimization
• Quantum state reconstruction from incomplete data
• Statistical Structure of Quantum Theory

Cited in

(6)

• Sensitivity statistical estimates for local a posteriori inference matrix-vector equations in algebraic Bayesian networks over quantum propositions
• A non-commutative Bayes' theorem
• Picturing classical and quantum Bayesian inference
• Online variance minimization
• Automorphisms for the logarithmic product of positive semidefinite operators
• Linear Algebra and Bayes’ Theorem in Probability

This page was built for publication: Bayesian generalized probability calculus for density matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1959541)