Continuity of the Maximum-Entropy Inference

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.

34 pages, 1 figure

References in corpus (7)

• On the quantum, classical and total amount of correlations in a quantum state
• Updating Probabilities
• Continuity of quantum channel capacities
• Roofs and Convexity
• Incomplete quantum process tomography and principle of maximal entropy
• Comment on some results of Erdahl and the convex structure of reduced density matrices
• On a Differential Geometric Viewpoint of Jaynes' Maxent Method and its Quantum Extension

Cited by in corpus (9)

• Continuity of the maximum-entropy inference: Convex geometry and numerical ranges approach
• Theoretical investigations of an information geometric approach to complexity
• A new signature of quantum phase transitions from the numerical range
• Maximum-entropy inference and inverse continuity of the numerical range
• Pre-images of extreme points of the numerical range, and applications
• A variation principle for ground spaces
• Discontinuities in the Maximum-Entropy Inference
• An information geometric perspective on the complexity of macroscopic predictions arising from incomplete information
• Matrix systems, algebras, and open maps