Learning Properties of Quantum States Without the I.I.D. Assumption

Abstract

We develop a framework for learning properties of quantum states beyond the assumption of independent and identically distributed (i.i.d.) input states. We prove that, given any learning problem (under reasonable assumptions), an algorithm designed for i.i.d. input states can be adapted to handle input states of any nature, albeit at the expense of a polynomial increase in training data size (aka sample complexity). Importantly, this polynomial increase in sample complexity can be substantially improved to polylogarithmic if the learning algorithm in question only requires non-adaptive, single-copy measurements. Among other applications, this allows us to generalize the classical shadow framework to the non-i.i.d. setting while only incurring a comparatively small loss in sample efficiency. We use rigorous quantum information theory to prove our main results. In particular, we leverage permutation invariance and randomized single-copy measurements to derive a new quantum de Finetti theorem that mainly addresses measurement outcome statistics and, in turn, scales much more favorably in Hilbert space dimension.

36+10 pages, 7 Figures. Close to the published version

References in corpus (18)

• Dynamical decoupling and noise spectroscopy with a superconducting flux qubit
• Efficient quantum state tomography
• Direct Fidelity Estimation from Few Pauli Measurements
• The randomized measurement toolbox
• One-and-a-half quantum de Finetti theorems
• Experimental demonstration of graph-state quantum secret sharing
• Experimental Verification of Multipartite Entanglement in Quantum Networks
• Quantum Anonymous Transmissions
• Matchgate Shadows for Fermionic Quantum Simulation
• Shallow shadows: Expectation estimation using low-depth random Clifford circuits
• Scalable and Flexible Classical Shadow Tomography with Tensor Networks
• Sample-efficient device-independent quantum state verification and certification
• Learning quantum states and unitaries of bounded gate complexity
• Thrifty shadow estimation: re-using quantum circuits and bounding tails
• Robust and efficient verification of graph states in blind measurement-based quantum computation
• Efficient verification of continuous-variable quantum states and devices without assuming identical and independent operations
• Sample-optimal classical shadows for pure states
• Quantum chi-squared tomography and mutual information testing

Cited by in corpus (3)

• Demonstration of Robust and Efficient Quantum Property Learning with Shallow Shadows
• Tight concentration inequalities for quantum adversarial setups exploiting permutation symmetry
• Experimental Verification of Entangled States in the Adversarial Scenario