The Quantum Relative Entropy as a Rate Function and Information Criteria
arXiv:1202.2943
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.
arXiv comment21 pages
References in corpus (9)
- Asymptotic Equivalence of Bayes Cross Validation and Widely Applicable Information Criterion in Singular Learning Theory
- Error Exponent in Asymmetric Quantum Hypothesis Testing and Its Application to Classical-Quantum Channel coding
- An Information-Spectrum Approach to Classical and Quantum Hypothesis Testing for Simple Hypotheses
- The Converse Part of The Theorem for Quantum Hoeffding Bound
- A quantum version of Sanov's theorem
- A New Strategy of Quantum-State Estimation for Achieving the Cramer-Rao Bound
- Accuracy of quantum-state estimation utilizing Akaike's information criterion
- Asymptotic Learning Curve and Renormalizable Condition in Statistical Learning Theory
- Micro-Macro Duality in Quantum Physics