Communications in Mathematical Physics

, Volume 330, Issue 3, pp 1263–1292 | Cite as

Continuity of the Maximum-Entropy Inference

Article

Abstract

We study the inverse problem of inferring the state of a finite-level quantum system from expected values of a fixed set of observables, by maximizing a continuous ranking function. We have proved earlier that the maximum-entropy inference can be a discontinuous map from the convex set of expected values to the convex set of states because the image contains states of reduced support, while this map restricts to a smooth parametrization of a Gibbsian family of fully supported states. Here we prove for arbitrary ranking functions that the inference is continuous up to boundary points. This follows from a continuity condition in terms of the openness of the restricted linear map from states to their expected values. The openness condition shows also that ranking functions with a discontinuous inference are typical. Moreover it shows that the inference is continuous in the restriction to any polytope which implies that a discontinuity belongs to the quantum domain of non-commutative observables and that a geodesic closure of a Gibbsian family equals the set of maximum-entropy states. We discuss eight descriptions of the set of maximum-entropy states with proofs of accuracy and an analysis of deviations.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alfsen E.M., Shultz F.W.: State Spaces of Operator Algebras: Basic Theory, Orientations and C*-Products. Birkhäuser, Boston (2001)CrossRefGoogle Scholar
  2. 2.
    Ali S.A., Cafaro C., Giffin A., Lupo C., Mancini S.: On a differential geometric viewpoint of Jaynes’ MaxEnt method and its quantum extension. AIP Conf. Proc. 1443, 120–128 (2012)CrossRefADSGoogle Scholar
  3. 3.
    Amari, S.: Differential-Geometrical Methods in Statistics. Lecture Notes in Statistics, vol. 28. Springer, Berlin (1985)Google Scholar
  4. 4.
    Amari S., Nagaoka, H.: Methods of Information Geometry. AMS Translations of Mathematical Monographs, vol. 191 (2000)Google Scholar
  5. 5.
    Ay N.: An information-geometric approach to a theory of pragmatic structuring. Ann. Probab. 30, 416–436 (2002)CrossRefMATHMathSciNetGoogle Scholar
  6. 6.
    Ayupov S.H., Rakhimov A., Usmanov S.H.: Jordan, Real and Lie Structures in Operator Algebras. Kluwer, Dordrecht (1997)CrossRefMATHGoogle Scholar
  7. 7.
    Barndorff-Nielsen O.: Information and Exponential Families in Statistical Theory. Wiley, New York (1978)MATHGoogle Scholar
  8. 8.
    Berge C.: Topological Spaces. Dover Publications, Inc., New York (1997)Google Scholar
  9. 9.
    Bjelaković I., Deuschel J.-D., Krüger T., Seiler R., Siegmund-Schultze R., Szkoła A.: A quantum version of Sanov’s theorem. Commun. Math. Phys. 260, 659–671 (2005)CrossRefMATHADSGoogle Scholar
  10. 10.
    Boltzmann L.: Über die Beziehung zwischen dem zweiten Hauptsatze der mechanischen Wärmetheorie und der Wahrscheinlichkeitsrechnung respektive den Sätzen über das Wärmegleichgewicht. Wien. Ber. 76, 373–435 (1877)Google Scholar
  11. 11.
    Bratteli O., Robinson D.W.W.: Operator Algebras and Quantum Statistical Mechanics 2: Equilibrium States. Models in Quantum Statistical Mechanics. Springer, Berlin (1997)CrossRefMATHGoogle Scholar
  12. 12.
    Bužek V., Drobný G., Derka R., Adam G., Wiedemann H.: Quantum state reconstruction from incomplete data. Chaos Solitons Fractals 10, 981–1074 (1999)CrossRefMATHMathSciNetGoogle Scholar
  13. 13.
    Caticha, A.: Entropic Inference and the Foundations of Physics, Brazilian Chapter of the International Society for Bayesian Analysis-ISBrA, Sao Paulo, Brazil (2012)Google Scholar
  14. 14.
    Caticha A., Giffin A.: Updating probabilities. AIP Conf. Proc. 872, 31–42 (2006)CrossRefADSGoogle Scholar
  15. 15.
    Čencov, N. N.: Statistical Decision Rules and Optimal Inference. AMS Translations of Mathematical Monographs, vol. 53 (1982); Original publication: Nauka (1972)Google Scholar
  16. 16.
    Chen J., Ji Z., Ruskai M.B., Zeng B.: Comment on some results of Erdahl and the convex structure of reduced density matrices. J. Math. Phys. 53, 072203 (2012)CrossRefMathSciNetADSGoogle Scholar
  17. 17.
    Csiszár I.: On topological properties of f-divergences. Studia Sci. Math. Hungar. 2, 329–339 (1967)MATHMathSciNetGoogle Scholar
  18. 18.
    Csiszár I.: I-Divergence geometry of probability distributions and minimization problems. Ann. Prob. 3, 146–158 (1975)CrossRefMATHGoogle Scholar
  19. 19.
    Csiszár I.: Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems. Ann. Statist. 19, 2032–2066 (1991)CrossRefMATHMathSciNetGoogle Scholar
  20. 20.
    Csiszár I., Matúš F.: Information projections revisited. IEEE Trans. Inf. Theory 49, 1474–1490 (2003)CrossRefMATHGoogle Scholar
  21. 21.
    Davies E.B., Lewis J.T.: An operational approach to quantum probability. Commun. Math. Phys. 17, 239–260 (1970)CrossRefMATHMathSciNetADSGoogle Scholar
  22. 22.
    Dudley R.M.: Consistency of M-estimators and one-sided bracketing. Progr. Probab. Birkhäuser 43, 33–58 (1998)MathSciNetGoogle Scholar
  23. 23.
    Greenberger D., Hentschel K., Weinert F.: Compendium of Quantum Physics: Concepts, Experiments, History and Philosophy. Springer, Berlin (2009)CrossRefGoogle Scholar
  24. 24.
    Groisman B., Popescu S., Winter A.: Quantum, classical, and total amount of correlations in a quantum state. Phys. Rev. A 72, 032317 (2005)CrossRefMathSciNetADSGoogle Scholar
  25. 25.
    Harremoës, P.: Information topologies with applications. In: Entropy, Search, Complexity, vol. 16, pp. 113–150. Bolyai Society Mathematical Studies (2007)Google Scholar
  26. 26.
    Hasegawa H.: Exponential and mixture families in quantum statistics: dual structure and unbiased parameter estimation. Rep. Math. Phys. 39, 49–68 (1997)CrossRefMATHMathSciNetADSGoogle Scholar
  27. 27.
    Henrion D.: Semidefinite representation of convex hulls of rational varieties. Acta Appl. Math. 115, 319–327 (2011)CrossRefMATHMathSciNetGoogle Scholar
  28. 28.
    Holevo, A.S.: Statistical Problems in Quantum Physics. Lecture Notes in Mathematics, vol. 330, pp. 104–119. Springer, Berlin (1973)Google Scholar
  29. 29.
    Ingarden R.S., Kossakowski A., Ohya M.: Information Dynamics and Open Systems. Kluwer, Dordrecht (1997)CrossRefMATHGoogle Scholar
  30. 30.
    Jaynes E.T.: Information theory and statistical mechanics. Phys. Rev. 106, 620–630 (1957)CrossRefMATHMathSciNetADSGoogle Scholar
  31. 31.
    Jenčová, A.: Geometry of quantum states: Dual connections and divergence functions. Rep. Math. Phys. 47, 121–138 (2001)Google Scholar
  32. 32.
    Karbelkar S.N.: On the axiomatic approach to the maximum entropy principle of inference. Pramāna J. Phys. 26, 301–310 (1986)CrossRefADSGoogle Scholar
  33. 33.
    Leung D., Smith G.: Continuity of quantum channel capacities. Commun. Math. Phys. 292, 201–215 (2009)CrossRefMATHMathSciNetADSGoogle Scholar
  34. 34.
    Li B.: Real Operator Algebras. World Scientific, Singapore (2003)CrossRefMATHGoogle Scholar
  35. 35.
    Lima Å.: On continuous convex functions and split faces. Proc. Lond. Math. Soc. 25, 27–40 (1972)CrossRefMATHMathSciNetGoogle Scholar
  36. 36.
    Modi K., Paterek T., Son W., Vedral V., Williamson M.: Unified view of quantum and classical correlations. Phys. Rev. Lett. 104, 080501 (2010)CrossRefMathSciNetADSGoogle Scholar
  37. 37.
    Nagaoka, H.: Differential geometrical aspects of quantum state estimation and relative entropy. In: Hirota, et al. (eds.) Quantum Communications and Measurement, pp. 449–452. Plenum Press, New York (1995)Google Scholar
  38. 38.
    Netzer T., Plaumann D., Schweighofer M.: Exposed faces of semidefinitely representable sets. Siam J. Optim. 20, 1944–1955 (2010)CrossRefMATHMathSciNetGoogle Scholar
  39. 39.
    Nielsen M.A., Chuang I.L.: Quantum Computation and Quantum Information. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
  40. 40.
    Papadopoulou S.: On the geometry of stable compact convex sets. Math. Ann. 229, 193–200 (1977)CrossRefMATHMathSciNetGoogle Scholar
  41. 41.
    Petz D.: Geometry of canonical correlation on the state space of a quantum system. J. Math. Phys. 35, 780–795 (1994)CrossRefMATHMathSciNetADSGoogle Scholar
  42. 42.
    Petz, D.: Quantum Information Theory and Quantum Statistics, Theoretical and Mathematical Physics. Springer, Berlin (2008)Google Scholar
  43. 43.
    Protasov V.Y., Shirokov M.E.: Generalized compactness in linear spaces and its applications. Sbornik Math. 200, 697–722 (2009)CrossRefMATHMathSciNetADSGoogle Scholar
  44. 44.
    Rockafellar R.T.: Convex Analysis. Princeton University Press, Princeton (1972)Google Scholar
  45. 45.
    Ruskai M.B.: Extermal properties of relative entropy in quantum statistical mechanics. Rep. Math. Phys. 26, 143–150 (1988)CrossRefMATHMathSciNetADSGoogle Scholar
  46. 46.
    Schrödinger E.: Die gegenwärtige situation in der Quantenmechanik. Die Naturwissenschaften 23, 807–849 (1935)CrossRefADSGoogle Scholar
  47. 47.
    Schweighofer, M., Sturmfels, B., Thomas, R.: Convex algebraic geometry. Banff Workshop Report (2010)Google Scholar
  48. 48.
    Shannon, C.E.: A mathematical theory of communication. Bell. Syst. Tech. J. 27, 379–423 and 623–656 (1948)Google Scholar
  49. 49.
    Shirokov, M.E.: Entropy characteristics of subsets of states. I. Izvestiya Math. 70, 1265–1292 (2006)Google Scholar
  50. 50.
    Shirokov M.E.: The Holevo capacity of infinite dimensional channels and the additivity problem. Commun. Math. Phys. 262, 137–159 (2006)CrossRefMATHMathSciNetADSGoogle Scholar
  51. 51.
    Shore, J.E., Johnson, R.W.: Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy. IEEE Trans. Inf. Theory 26, 26–37 (1980); Correction ibid. 29, 942–943 (1983)Google Scholar
  52. 52.
    Skilling, J.: The axioms of maximum entropy. In: Erickson, G.J., Smith, C.R. (eds.) Maximum-Entropy and Bayesian Methods in Science and Engineering, pp. 173–187, Kluwer, Dordrecht (1988)Google Scholar
  53. 53.
    Topsøe F.: Information theoretical optimization techniques. Kybernetika 15, 8–27 (1979)MathSciNetGoogle Scholar
  54. 54.
    Uffink J.: Can the maximum entropy principle be explained as a consistency requirement?. Stud. Hist. Phil. Sci. B 26, 223–261 (1995)MATHMathSciNetGoogle Scholar
  55. 55.
    Uffink, J.: Compendium of the foundations of classical statistical physics. In: Butterfield, J., Earman, J. (eds.) Handbook of the Philosophy of Science, pp. 924–1074. Elsevier, Amsterdam (2007)Google Scholar
  56. 56.
    Uhlmann A.: Roofs and convexity. Entropy 12, 1799–1832 (2010)CrossRefMATHMathSciNetADSGoogle Scholar
  57. 57.
    Umegaki H.: Conditional expectation in an operator algebra. IV. Kōdai Math. Sem. Rep. 14, 59–85 (1962)CrossRefMATHMathSciNetGoogle Scholar
  58. 58.
    Voigt I., Weis S.: Polyhedral Voronoi cells. Contrib. Algeb. Geometry 51, 587–598 (2010)MATHMathSciNetGoogle Scholar
  59. 59.
    von Neumann, J.: Thermodynamik quantenmechanischer Gesamtheiten. Gött. Nach. 273–291 (1927)Google Scholar
  60. 60.
    Wehrl A.: General properties of entropy. Rev. Modern Phys. 50, 221–260 (1978)CrossRefMathSciNetADSGoogle Scholar
  61. 61.
    Weis, S.: Exponential families with incompatible statistics and their entropy distance. PhD Dissertation, Friedrich-Alexander University Erlangen-Nürnberg (2010)Google Scholar
  62. 62.
    Weis, S.: Quantum convex support. Lin. Alg. Appl. 435, 3168–3188 (2011); correction: 436, xvi (2012)Google Scholar
  63. 63.
    Weis S.: A note on touching cones and faces. J. Convex Anal. 19, 323–353 (2012)MATHMathSciNetGoogle Scholar
  64. 64.
    Weis S., Knauf A.: Entropy distance: New quantum phenomena. J. Math. Phys. 53, 102206 (2012)CrossRefMathSciNetADSGoogle Scholar
  65. 65.
    Weis, S.: Information topologies on non-commutative state spaces. J. Convex Anal. 21 (in press)Google Scholar
  66. 66.
    Wichmann E.H.: Density matrices arising from incomplete measurements. J. Math. Phys. 4, 884–896 (1963)CrossRefMATHMathSciNetADSGoogle Scholar
  67. 67.
    Ziman, M.: Incomplete quantum process tomography and principle of maximal entropy. Phys. Rev. A 78, 032118 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Max-Planck-Institute for Mathematics in the SciencesLeipzigGermany

Personalised recommendations