Bayesian generalized probability calculus for density matrices

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.

[1]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[2]  Joseph M. Renes,et al.  Gleason-Type Derivations of the Quantum Probability Rule for Generalized Measurements , 2004 .

[3]  Manfred K. Warmuth A Bayes Rule for Density Matrices , 2005, NIPS.

[4]  C. Adami,et al.  Quantum extension of conditional probability , 1999 .

[5]  C. Caves,et al.  Quantum Bayes rule , 2000, quant-ph/0008113.

[6]  John K. Tomfohr,et al.  Lecture Notes on Physics , 1879, Nature.

[7]  Thierry Paul,et al.  Quantum computation and quantum information , 2007, Mathematical Structures in Computer Science.

[8]  P. Dooren Matrix Mathematics: Theory, Facts, and Formulas with Application to Linear Systems Theory [Book Review] , 2006 .

[9]  Stefan Weigert Quantum State Reconstruction , 2009, Compendium of Quantum Physics.

[10]  Matteo G. A. Paris,et al.  Quantum estimation via the minimum Kullback entropy principle , 2007, 0708.0956.

[11]  Marc Alexa,et al.  Linear combination of transformations , 2002, ACM Trans. Graph..

[12]  R. Feynman Statistical Mechanics, A Set of Lectures , 1972 .

[13]  O. Seeberg Statistical Mechanics. — A Set of Lectures , 1975 .

[14]  Manfred K. Warmuth,et al.  Online variance minimization , 2011, Machine Learning.

[15]  Manfred K. Warmuth,et al.  Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension , 2006, NIPS.

[16]  Manfred K. Warmuth Winnowing subspaces , 2007, ICML '07.

[17]  Manfred K. Warmuth,et al.  Additive versus exponentiated gradient updates for linear prediction , 1995, STOC '95.

[18]  B. Simon Functional integration and quantum physics , 1979 .

[19]  A. Zellner Optimal Information Processing and Bayes's Theorem , 1988 .

[20]  V. Buzek,et al.  Quantum State Reconstruction From Incomplete Data , 1998 .

[21]  Gunnar Rätsch,et al.  Matrix Exponentiated Gradient Updates for On-line Learning and Bregman Projection , 2004, J. Mach. Learn. Res..

[22]  Paul Lamere,et al.  Classification with free energy at raised temperatures , 2003, INTERSPEECH.

[23]  Manfred K. Warmuth,et al.  Randomized Online PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension , 2008 .

[24]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[25]  A. Gleason Measures on the Closed Subspaces of a Hilbert Space , 1957 .

[26]  Dirk-Gunnar Welsch,et al.  Quantum‐State Reconstruction , 2006 .

[27]  Manfred K. Warmuth,et al.  Averaging Expert Predictions , 1999, EuroCOLT.

[28]  A. Holevo Statistical structure of quantum theory , 2001 .

[29]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[30]  A. Moore,et al.  Forecasting Web Page Views: Methods and Observations , 2008 .