Abstract
We prove that the quantum relative entropy is a rate function in large deviation principle. Next, we define information criteria for quantum states and estimate the accuracy of the use of them. Most of the results in this paper are essentially based on Hiai-Ohya-Tsukada theorem.
Similar content being viewed by others
Notes
A positive linear functional \(\rho \) on a von Neumann algebra \(\mathcal M \) on \(\mathcal H \) is said to be normal if there exists a positive trace class operator \(\sigma \in {\varvec{T}}(\mathcal H )_{+}\) such that \(\rho (A)=\mathrm Tr [\sigma A]\) for each \(A\in \mathcal M \).
A measure \(\mu \) on a Borel space \(K\) is said to be pseudosupported by an arbitrary set \(A\subseteq K\) if \(\mu (B)=0\) for all Baire sets \(B\) such that \(B\cap A=\emptyset \).
The set of factor states \(F_\mathfrak{A }\) on \(\mathfrak A \) is not always Borel measurable. If a \(\text{ C}^*\)-algebra \(\mathfrak A \) is separable, \(F_\mathfrak{A }\) is Borel measurable and the central measure \(\mu _\omega \) of \(\omega \in E_\mathfrak A \) is supported by \(F_\mathfrak{A }\).
The injective \(\text{ C}^{*}\)-tensor product \(\mathfrak A _{1}\otimes \mathfrak A _{2}=\mathfrak A _{1}\otimes _{min} \mathfrak A _{2}\) of two \(\text{ C}^{*}\)-algebras \(\mathfrak A _{1}\) and \(\mathfrak A _{2}\) is the completion of the algebraic tensor product \(\mathfrak A _{1}\otimes _{alg} \mathfrak A _{2}\) by the norm \(\Vert \cdot \Vert _{min}\) defined by \(\Vert C\Vert _{min}=\sup \Vert (\pi _{1}\otimes \pi _{2})(C)\Vert , C\in \mathfrak A _{1}\otimes _{alg} \mathfrak A _{2}\), where \(\pi _{1}\) and \(\pi _{2}\) run over all representations of \(\mathfrak A _{1}\) and \(\mathfrak A _{2}\), respectively. The tensor product \(\omega _1\otimes \omega _2\in E_\mathfrak{A _{1}\otimes \mathfrak A _{2}}\) of states \(\omega _1\in E_\mathfrak{A _1}\) and \(\omega _2\in E_\mathfrak{A _2}\) is defined as the state \(\omega \) satisfying \(\omega (A_1\otimes A_2)=\omega _1(A_1)\omega _2(A_2)\) for \(A\in \mathfrak A _1, A\in \mathfrak A _2\). See [46], in detail.
A standard form of a von Neumann algebra \(\mathcal M \) on a Hilbert space \(\mathcal H \) is a quadtuple \((\mathcal M ,\mathcal H ,J,\mathcal P )\) constituting of \(\mathcal M , \mathcal H \), a unitary involution \(J\), a self-dual cone \(\mathcal P \) in \(\mathcal H \), which satisfy the followings: (i) \(J\mathcal M J=\mathcal M ^\prime \); (ii) \(JAJ=A^*, A\in \mathfrak Z (\mathcal M )\); (iii) \(J\xi =\xi , \xi \in \mathcal P \); (iv) \(AJAJ\mathcal P \subset \mathcal P , A\in \mathcal M \). See [47].
See [11, p. 263].
References
Aitchison, J.: Goodness of prediction fit. Biometrika 62, 547–554 (1975)
Akaike, H.: A new look at the statistical model identification. IEEE Trans. Autom. Control 19, 716–723 (1974)
Amari, S., Nagaoka, H.: Methods of Information Geometry, Translations of mathematical monographs, vol. 191. Amer. Math. Soc. & Oxford Univ.Press (2000)
Araki, H.: Relative Entropy for States of Von Neumann Algebras II. Publ. RIMS, Kyoto Univ. vol. 13, pp. 173–192 (1977)
Audenaert, K.M.R., Calsamiglia, J., Munoz-Tapia, R., Bagan, E., Masanes, L., Acin, A., Verstraete, F.: Discriminating states: the quantum Chernoff bound. Phys. Rev. Lett. 98, 160501 (2007)
Bjelakovic, I., Deuschel, J.-D., Kruger, T., Seiler, R., Siegmund-Schultze, R., Szkola, A.: A quantum version of Sanov’s theorem. Commun. Math. Phys. 260, 659–671 (2006)
Bratteli, O., Robinson, D.W.: Operator Algebras and Quantum Statistical Mechanics, 2nd printing of 2nd edn, vol. 1. Springer (2002)
Corcuera, J.M., Giummolè, F.: A generalized Bayes rule for prediction. Scand. J. Stat. 26, 265 (1999)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, New York (1991)
Csiszár, I.: A simple proof of Sanov’s theorem. Bull. Brazilian Math. Soc. 37, 453–459 (2006)
Dembo, A., Zeitouni, O.: Large Deviations Techniques and Applications, 2nd edn. Springer, Berlin (2002)
Drton, M., Sturmfels, B., Sullivant, S.: Lectures on Algebraic Statistics. Birkhäuser (2008)
Harada, R., Ojima, I.: A unified scheme of measurement and amplification processes based on Micro-Macro duality-Stern-Gerlach experiment as a typical example. Open Syst. Inf. Dyn. 16, 55–74 (2009)
Hayashi, M.: Error exponent in asymmetric quantum hypothesis testing and its application to classical-quantum channel coding. Phys. Rev. A 76, 062301 (2007)
Helstrom, C.W.: Quantum Detection and Estimation Theory. Academic Press, New York (1976)
Hiai, F., Mosonyi, M., Petz, D., Bény, C.: Quantum f-Divergence and error Correction. Rev. Math. Phys. 23, 691–747 (2011)
Hiai, F., Ohya, M., Tsukada, M.: Sufficiency and relative entropy in *-algebras with applications in quantum systems. Pac. J. Math. 107, 117–140 (1983)
Hiai, F., Petz, D.: The proper formula for relative entropy and its asymptotics in quantum probability. Commun. Math. Phys. 143, 99–114 (1991)
Holevo, A.S.: Probabilistic and Statistical Aspects of Quantum Theory. North-Holland, Amsterdam (1982)
Jaksic, V., Ogata, Y., Pautrat, Y., Pillet, C.-A.: Entropic fluctuations in quantum statistical mechanics. An introduction. In: Quantum Theory from Small to Large Scales, Lecture Notes of the Les Houches Summer School, vol. 95, August 2010. Oxford University Press, USA (2012)
Jaksic, V., Ogata, Y., Pillet, C.-A., Seiringer, R.: Quantum hypothesis testing and non-equilibrium statistical mechanics. Rev. Math. Phys. 24, 1230002 (2012)
Jenova, A., Petz, D.: Sufficiency in quantum statistical inference. Commun. Math. Phys. 263, 259–276 (2006)
Lehmann, E.L., Romano, J.P.: Testing Statistical Hypotheses, 3rd edn. Springer, New York (2005)
Nagaoka, H.: The Converse Part of the Theorem for Quantum Hoeffding Bound. arXiv:quant-ph/0611289 (2006)
Nagaoka, H., Hayashi, M.: An information-spectrum approach to classical and quantum hypothesis testing for simple hypotheses. IEEE Trans. Inf. Theory 53, 534–549 (2007)
Nielsen, M., Chuang, I.: Quantum Computation and Quantum Information. Cambridge Univ. Press, Cambridge (2000)
Nussbaum, M., Szkola, A.: The Chernoff lower bound for symmetric quantum hypothesis testing. Ann. Stat. 37, 1040–1057 (2009)
Ogata, Y.: Large deviations in quantum spin chains. Commun. Math. Phys. 296, 35–68 (2010)
Ogawa, T., Hayashi, M.: On error exponents in quantum hypothesis testing. IEEE Trans. Inf. Theory 50, 1368–1372 (2004)
Ogawa, T., Nagaoka, H.: Strong converse and Stein’s lemma in quantum hypothesis testing. IEEE Trans. Inf. Theory 46, 2428–2433 (2000)
Ojima, I.: A unified scheme for generalized sectors based on selection criteria-order parameters of symmetries and of thermality and physical meanings of adjunctions. Open Syst. Inf. Dyn. 10, 235–279 (2003)
Ojima, I.: Micro-macro duality in quantum physics. In: Proceedings of International Conference on Stochastic Analysis, Classical and Quantum, pp. 143–161. World Scientific, Singapore (2005). arXiv:math-ph/0502038
Ojima, I.: Micro-macro duality and space-time emergence. In: Proceedings of International Conference, “Advances in Quantum Theory”, pp. 197–206 (2011)
Ojima, I., Okamura, K.: Large devation strategy for inverse problem I. Open Syst. Inf. Dyn. 19, 1250021 (2012)
Ojima, I., Okamura, K.: Large devation strategy for inverse problem II. Open Syst. Inf. Dyn. 19, 1250022 (2012)
Ojima, I., Okamura, K., Saigo, H. (in preparation)
Ozawa, M.: Quantum measuring processes of continuous obsevables. J. Math. Phys. 25, 79–87 (1984)
Ozawa, M.: Quantum perfect correlations, Ann. Phys. (N.Y.), 321, 744–769 (2006)
Ohya, M., Petz, D.: Qunatum Entropy and Its Use. Springer, Berlin (1993)
Petz, D.: Quasi-entropies for states of a von Neumann algebra. Publ. RIMS Kyoto Univ. 21, 787–800 (1985)
Petz, D.: A variational expression for the relative entropy. Commun. Math. Phys. 114, 345–349 (1988)
Petz, D.: First steps towards a Donsker and Varadhan theory in operator algebras. In: Quantum Probability and Applications, V. Lec. Notes in Math. vol. 1442, pp. 311–319 (1990)
Petz, D., Raggio, G.A., Verbeure, A.: Asymptotics of Varadhan-type and the Gibbs variational principle. Commun. Math. Phys. 121, 271–282 (1989)
Rényi, A.: Wahrscheinlichkeitsrechnung. VED Deutsch, Ver der Wiss, Berlin (1962)
Rényi, A.: On the foundations of information theory. Rev. Int. Stat. Inst. 33, 1–14 (1965)
Takesaki, M.: Theory of Operator Algebras I. Springer, Berlin (1979)
Takesaki, M.: Theory of Operator Algebras II. Springer, Berlin (2002)
Tanaka, F.: Generalized Bayesian predictive density operator. In: Proceedings of 14th Quantum Information Technology Symposium (QIT14), Tokyo, Japan, May 29–30, pp. 107–110 (2006)
Tanaka, F., Komaki, F.: Bayesian predictive density operators for exchangeable quantum-statistical models. Phys. Rev. A 71, 052323 (2005)
Uhlmann, A.: Relative entropy and the Wigner-Yanase-Dyson-Lieb concavity in an interpolation theory. Commun. Math. Phys. 54, 21–32 (1977)
Usami, K., Nambu, Y., Tsuda, Y., Matsumoto, K., Nakamura, K.: Accuracy of quantum-state estimation utilizing Akaike’s information criterion. Phys. Rev. A 68, 022314 (2003)
Watanabe, S.: Algebraic Geometry and Statistical Learning Theory. Cambridge University Press, Cambridge (2009)
Watanabe, S.: Asymptotic learning curve and renormalizable condition in statistical learning theory. J. Phys. Conf. Ser. 233, 012014 (2010)
Watanabe, S.: Asymptotic equivalence of Bayes cross validation and widely applicable information criterion in singular learning theory. J. Mach. Lear. Res. 11, 3571–3591 (2010)
Yin, J.O.S., van Enk, S.J.: Information criteria for efficient quantum state estimation. Phys. Rev. A 83, 062110 (2011)
Acknowledgments
The author would like to thank Prof. Izumi Ojima, Dr. Hayato Saigo, Dr. Takahiro Hasebe, Dr. Hiroshi Ando for their warm encouragement and useful comments. He also thanks anonymous referees for their valuable comments to improve the paper.
Author information
Authors and Affiliations
Corresponding author
Proofs of Theorems
Proofs of Theorems
Proof of Theorem 7
It suffices to prove for \(|\alpha |<1\). It is proved by discussion in [17, p. 129] that
Therefore, we have
\(\square \)
Proof of Theorem 8
It suffices to prove for \(|\alpha |<1\). By [17, Lemma 3.1], it is proved that
where \(\pi =\pi _{\varphi +\psi }\). Thus we have
\(\square \)
Lemma 4
Let \(\varphi |_\mathcal{B }, \psi |_\mathcal{B }\) be the restrictions of states \(\varphi ,\psi \) on a von Neumann algebra \(\mathcal M \) to a \(*\)-subalgebra \(\mathcal B \) to \(\mathcal M \). Then,
Proof
It suffices to prove it for \(|\alpha |<1\). \(|_\mathcal{B }:E_\mathcal M \rightarrow E_\mathcal B \) is the dual of the embedding \(\mathcal B \ni B \mapsto B\in \mathcal M \). Using [50, Proposition 9] and Theorem 8,
Thus we have
\(\square \)
Proof of Theorem 9
It suffices to prove for \(|\alpha |<1\).
We define \(\Gamma : \mathfrak A \rightarrow C(E_\mathfrak A )\) by \(\Gamma (A)(\rho )=\rho (A)\), and its dual map \(\Gamma ^*:M_1(E_\mathfrak A )\rightarrow E_\mathfrak A \) by
for \(\lambda \in M_1(E_\mathfrak A )\). \(\Gamma \) satisfies
for any \(A\in \mathfrak A \). Thus,
By assumption, \(m\) is a subcentral measure \(\mu _\mathcal{C }\) associated with a von Neumann subalgebra \(\mathcal C \) of the center \(\mathfrak Z _\chi (\mathfrak A )=\pi _{\chi }(\mathfrak A )^{\prime \prime }\cap \pi _{\chi }(\mathfrak A )^{\prime }\) of a state \(\chi \in E_\mathfrak{A }\). We define a \(*\)-isomorphism \(\kappa _m:L^\infty (E_\mathfrak A ,m)\rightarrow \mathcal C \) by
It is then proved in [17, Example 2.6 and Theorem 3.2] that
where \(\tilde{\varphi }, \tilde{\psi }\) are the normal extensions of \(\varphi , \psi \) to \(\pi _{\chi }(\mathfrak A )^{\prime \prime }\). By Lemma 4,
\(\square \)
Rights and permissions
About this article
Cite this article
Okamura, K. The quantum relative entropy as a rate function and information criteria. Quantum Inf Process 12, 2551–2575 (2013). https://doi.org/10.1007/s11128-013-0540-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11128-013-0540-x