Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing

Abstract

A quantum generalized divergence by definition satisfies the data-processing inequality; as such, the relative decrease in such a divergence under the action of a quantum channel is at most one. This relative decrease is formally known as the contraction coefficient of the channel and the divergence. Interestingly, there exist combinations of channels and divergences for which the contraction coefficient is strictly less than one. Furthermore, understanding the contraction coefficient is fundamental for the study of statistical tasks under privacy constraints. To this end, here we establish upper bounds on contraction coefficients for the hockey-stick divergence under privacy constraints, where privacy is quantified with respect to the quantum local differential privacy (QLDP) framework, and we fully characterize the contraction coefficient for the trace distance under privacy constraints. With the machinery developed, we also determine an upper bound on the contraction of both the Bures distance and quantum relative entropy relative to the normalized trace distance, under QLDP constraints. Next, we apply our findings to establish bounds on the sample complexity of quantum hypothesis testing under privacy constraints. Furthermore, we study various scenarios in which the sample complexity bounds are tight, while providing order-optimal quantum channels that achieve those bounds. Lastly, we show how private quantum channels provide fairness and Holevo information stability in quantum learning settings.

v3:typo corrected in Proposition 10; 36 pages; See independent work titled "Sample Complexity of Locally Differentially Private Quantum Hypothesis Testing" by Hao-Chung Cheng, Christoph Hirche, and Cambyse Rouzé

References in corpus (18)

• RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response
• On quantum Renyi entropies: a new generalization and some properties
• The Quantum Chernoff Bound
• Strong converse for the classical capacity of entanglement-breaking and Hadamard channels via a sandwiched Renyi relative entropy
• Min- and Max- Relative Entropies and a New Entanglement Monotone
• Quantum state discrimination and its applications
• Asymptotic Error Rates in Quantum Hypothesis Testing
• The Chernoff lower bound for symmetric quantum hypothesis testing
• Differential Privacy as a Mutual Information Constraint
• Quantum noise protects quantum classifiers against adversaries
• Continuity bounds on the quantum relative entropy
• Second-order asymptotics for source coding, dense coding and pure-state entanglement conversions
• Quantum Differentially Private Sparse Regression Learning
• Quantum Rényi and $f$-divergences from integral representations
• Quantum Pufferfish Privacy: A Flexible Privacy Framework for Quantum Systems
• Pufferfish Privacy: An Information-Theoretic Study
• A lower bound on the fidelity between two states in terms of their trace-distance and max-relative entropy
• Information-theoretic generalization bounds for learning from quantum data

Cited by in corpus (4)

• An invitation to the sample complexity of quantum hypothesis testing
• Measured Hockey-Stick Divergence and its Applications to Quantum Pufferfish Privacy
• Quantum Local Differential Privacy and Quantum Statistical Query Model
• Sample Complexity Bounds for Scalar Parameter Estimation Under Quantum Differential Privacy