The minimum change principle provides an information-theoretic characterization of the Bayes reversal channel in classical probability theory and has recently been proposed as a framework for extending Bayes' rule to quantum information theory. Using quantum relative entropy, we investigate a minimum change principle for the setting of quantum statistical inference. Specifically, we consider a forward process based on a classical-to-quantum preparation channel and a reverse process based on a quantum-to-classical measurement channel. We establish a closed-form characterization of measurements that are optimal for this principle, and this optimal measurement can be found via a dual formulation involving a single unconstrained Hermitian variable. This perspective allows us to recover some notable measurements within the same framework, including pretty good measurements and Fermi-Dirac thermal measurements, and we use it to discover a novel family that we call softmin thermal measurements. We further show that softmin thermal measurements arise as optimal solutions to entropy-regularized semidefinite optimization problems, demonstrating that they play a role for measurements analogous to that of thermal states in statistical mechanics. Finally, we prove an additivity property for the relative-entropy minimum change principle and investigate the performance of Fermi-Dirac thermal measurements for quantum hypothesis testing.
The minimum change principle provides an information-theoretic characterization of the Bayes reversal channel in classical probability theory and has recently been proposed as a framework for extending Bayes' rule to quantum information theory. Using quantum relative entropy, we investigate a minimum change principle for the setting of quantum statistical inference. Specifically, we consider a forward process based on a classical-to-quantum preparation channel and a reverse process based on a quantum-to-classical measurement channel. We establish a closed-form characterization of measurements that are optimal for this principle, and this optimal measurement can be found via a dual formulation involving a single unconstrained Hermitian variable. This perspective allows us to recover some notable measurements within the same framework, including pretty good measurements and Fermi-Dirac thermal measurements, and we use it to discover a novel family that we call softmin thermal measurements. We further show that softmin thermal measurements arise as optimal solutions to entropy-regularized semidefinite optimization problems, demonstrating that they play a role for measurements analogous to that of thermal states in statistical mechanics. Finally, we prove an additivity property for the relative-entropy minimum change principle and investigate the performance of Fermi-Dirac thermal measurements for quantum hypothesis testing.
Quantum measurements are the means by which we recover messages encoded into quantum states. They are at the forefront of quantum hypothesis testing, wherein the goal is to perform an optimal measurement for arriving at a correct conclusion. Mathematically, a measurement operator is Hermitian with eigenvalues in [0,1]. By noticing that this constraint on each eigenvalue is the same as that imposed on fermions by the Pauli exclusion principle, we interpret every eigenmode of a measurement operator as an independent effective fermionic mode. Under this perspective, various objective functions in quantum hypothesis testing can be viewed as the total expected energy associated with these fermionic occupation numbers. By instead fixing a temperature and minimizing the total expected fermionic free energy, we find that optimal measurements for these modified objective functions are Fermi-Dirac thermal measurements, wherein their eigenvalues are specified by Fermi-Dirac distributions. In the low-temperature limit, their performance closely approximates that of optimal measurements for quantum hypothesis testing, and we show that their parameters can be learned by classical or hybrid quantum-classical optimization algorithms. This leads to a new quantum machine-learning model, termed Fermi-Dirac machines, consisting of parameterized Fermi-Dirac thermal measurements-an alternative to quantum Boltzmann machines based on thermal states. Beyond hypothesis testing, we show how general semidefinite optimization problems can be solved using this approach, leading to a novel paradigm for semidefinite optimization on quantum computers, in which the goal is to implement thermal measurements rather than prepare thermal states. Finally, we propose quantum algorithms for implementing Fermi-Dirac thermal measurements, and we also propose second-order hybrid quantum-classical optimization algorithms.
Abstract Many quantum information measures can be written as an optimization of the quantum relative entropy between sets of states. For example, the relative entropy of entanglement of a state is the minimum relative entropy to the set of separable states. The various capacities of quantum channels can also be written in this way. We propose a unified framework to numerically compute these quantities using off-the-shelf semidefinite programming solvers, exploiting the approximation method proposed in Fawzi, Saunderson and Parrilo (2017 arXiv: 1705.00812). As a notable application, this method allows us to provide numerical counterexamples for a proposed lower bound on the quantum conditional mutual information in terms of the relative entropy of recovery.
A single classical f-divergence has several inequivalent quantum versions, but what distinguishes them operationally is less clear. Matsumoto's reverse tests characterize the maximal quantum f-divergence as the least classical distinguishability needed to prepare two quantum states with one device. Here we introduce retrodictive tests, in which two reverse tests sharing a reference state are coupled via Bayesian retrodiction to define a forward and a reverse stochastic process. In the forward process, the system is prepared by the first device and measured by the Petz transpose of the second; the reverse process interchanges their roles. We seek the least classical distinguishability between these two processes, as measured by the f-divergence between their joint laws, for fixed prescribed states and reference. For full-rank states in finite dimension, we prove that the canonical spectral implementations attain this minimum simultaneously for every operator-convex f. The reference then determines which quantum f-divergence is obtained: a flat reference gives the standard divergences, with the Nussbaum--Szkoła distributions as optimal joint laws; either prescribed state as reference recovers Matsumoto's reverse tests and the maximal divergences; and power references give the geodesic family. In particular, the Umegaki and Belavkin--Staszewski relative entropies arise from the same classical variational principle under different choices of reference. Spectral optimality extends to processes containing a quantum channel; for channels with full-rank Choi operator, the minimum of the forward relative entropy agrees with a known average entropy production.
Bayes' rule, which is routinely used to update beliefs based on new evidence, can be derived from a principle of minimum change. This principle states that updated beliefs must be consistent with new data, while deviating minimally from the prior belief. Here, we introduce a quantum analog of the minimum change principle and use it to derive a quantum Bayes' rule by minimizing the change between two quantum input-output processes, not just their marginals. This is analogous to the classical case, where Bayes' rule is obtained by minimizing several distances between the joint input-output distributions. When the change maximizes the fidelity, the quantum minimum change principle has a unique solution, and the resulting quantum Bayes' rule recovers the Petz transpose map in many cases.
The rapid advancement of quantum information science has spurred research into the ultimate performance limits of quantum systems in communication, sensing, and computation. This thesis adopts a decision-theoretic and information-theoretic viewpoint to systematically study fundamental problems in quantum statistical inference, with a focus on continuous-variable and bosonic platforms. The central theme is to uncover the interplay among physical structure (e.g., Gaussianity and phase-space geometry), operational restrictions (e.g., postselection and covariant measurements), and inference objectives (e.g., risk, error probability, and detection delay), and their joint impact on fundamental limits and attainability. The thesis first advances the understanding of phase-space entropy and the Wigner entropy conjecture. For Wigner-nonnegative quantum states, we develop verifiable sufficient criteria based on moment functionals and purity constraints, thereby extending the range of states for which the conjecture holds. We also establish explicit purity thresholds that guarantee the conjecture in the low-purity regime. These results reveal how Wigner nonnegativity constrains non-Gaussian structure and suggest pathways for incorporating further quantum-realizability conditions. Second, the thesis investigates the role of postselection in quantum state discrimination. We prove that, on average, environment-assisted partial postselection cannot outperform the Helstrom bound, yet conditional improvements are possible in selected branches. This clarifies the decision-theoretic trade-off between conditional performance and success probability, providing a rigorous basis for evaluating postselected protocols. In parameter estimation, we study phase-shift sensing within the covariant measurement framework. By linking the Bayesian risk to the Fourier coefficients of the input state, we derive an explicit characterization of optimal probe states via the Perron–Frobenius theorem and show that Heisenberg scaling is attainable in the high-energy limit. This offers constructive guidance for designing optimal sensing states under symmetry constraints. Finally, the thesis extends classical quickest change detection to sequential quantum inference. We establish the asymptotic relationship between quantum relative entropy and detection delay, and develop protocol architectures tailored to bosonic sensing and joint communication–detection tasks. In particular, for phase-change detection, we provide an analytic framework for computing quantum relative entropy with Gaussian probes, supplying a theoretical toolkit for practical system design. By integrating phase-space methods, information measures, and sequential decision theory, this thesis provides a cohesive analytical framework and delivers several substantive advances in quantum statistical inference for continuous-variable systems, with implications for quantum sensing, quantum communication, and quantum signal processing.
Abstract A quantum channel is sufficient with respect to a set of input states if it can be reversed on this set. In the approximate version, the input states can be recovered within an error bounded by the decrease of the relative entropy under the channel. Using a new integral representation of the relative entropy in Frenkel (Integral formula for quantum relative entropy implies data processing inequality, Quantum 7, 1102 (2023)), we present an easy proof of a characterization of sufficient quantum channels and recoverability by preservation of optimal success probabilities in hypothesis testing problems, equivalently, by preservation of L1 L 1 -distance.