Quantum Local Differential Privacy and Quantum Statistical Query Model

Abstract

Quantum statistical queries provide a theoretical framework for investigating the computational power of a learner with limited quantum resources. This model is particularly relevant in the current context, where available quantum devices are subject to severe noise and have limited quantum memory. On the other hand, the framework of quantum differential privacy demonstrates that noise can, in some cases, benefit the computation, enhancing robustness and statistical security. In this work, we establish an equivalence between quantum statistical queries and quantum differential privacy in the local model, extending a celebrated classical result to the quantum setting. Furthermore, we derive strong data processing inequalities for the quantum relative entropy under local differential privacy and apply this result to the task of asymmetric hypothesis testing with restricted measurements. Finally, we consider the task of quantum multi-party computation under local differential privacy. As a proof of principle, we demonstrate that the parity function is efficiently learnable in this model, whereas the corresponding classical task requires exponentially many samples.

arXiv commentThis version significantly extends the previous one with new entropic inequalities under local privacy, a private version of the quantum Stein's Lemma and an application to private multi-party quantum computation

References in corpus (32)

• Quantum Computing in the NISQ era and beyond
• Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer
• Supervised learning with quantum enhanced feature spaces
• Universal Quantum Computation with ideal Clifford gates and noisy ancillas
• Renyi Differential Privacy
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Noise-Induced Barren Plateaus in Variational Quantum Algorithms
• Min- and Max- Relative Entropies and a New Entanglement Monotone
• Quantum Information Processing with Finite Resources -- Mathematical Foundations
• Local Differential Privacy for Deep Learning
• Sampling from the thermal quantum Gibbs state and evaluating partition functions with a quantum computer
• Monotone Riemannian Metrics and Relative Entropy on Non-Commutative Probability Spaces
• Quantum noise protects quantum classifiers against adversaries
• Approximate unitary $t$-designs by short random quantum circuits using nearest-neighbor and long-range gates
• Measuring magic on a quantum processor
• Decoupling with random quantum circuits
• Stabilizer entropies are monotones for magic-state resource theory
• A polynomial-time classical algorithm for noisy random circuit sampling
• Towards quantum advantage via topological data analysis
• Secure Multi-party Quantum Computation with a Dishonest Majority
• A single $T$-gate makes distribution learning hard
• On contraction coefficients, partial orders and approximation of capacities for quantum channels
• Contraction coefficients for noisy quantum channels
• Families of completely positive maps associated with monotone metrics
• Learning quantum many-body systems from a few copies
• Quantum Rényi and $f$-divergences from integral representations
• Pauli path simulations of noisy quantum circuits beyond average case
• On the Hardness of PAC-learning Stabilizer States with Noise
• Efficient thermalization and universal quantum computing with quantum Gibbs samplers
• Contraction of Private Quantum Channels and Private Quantum Hypothesis Testing
• Mathematical comparison of classical and quantum mechanisms in optimization under local differential privacy
• Classical Verification of Quantum Learning