Deep Neural Network-assisted improvement of quantum compressed sensing tomography

Abstract

Quantum compressed sensing is the fundamental tool for low-rank density matrix tomographic reconstruction in the informationally incomplete case. We examine situations where the acquired information is not enough to allow one to obtain a precise compressed sensing reconstruction. In this scenario, we propose a Deep Neural Network-based post-processing to improve the initial reconstruction provided by compressed sensing. The idea is to treat the estimated state as a noisy input for the network and perform a deep-supervised denoising task. After the network is applied, a projection onto the space of feasible density matrices is performed to obtain an improved final state estimation. We demonstrate through numerical experiments the improvement obtained by the denoising process and exploit the possibility of looping the inference scheme to obtain further advantages. Finally, we test the resilience of the approach to out-of-distribution data.

11 pages, 8 figures, github hyperlink included

References in corpus (35)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Efficient quantum state tomography
• Quantum Error Mitigation
• Quantum Tomography via Compressed Sensing: Error Bounds, Sample Complexity, and Efficient Estimators
• Reconstructing quantum states with generative models
• Efficient tomography of a quantum many-body system
• Permutationally invariant quantum tomography
• Experimental neural network enhanced quantum tomography
• Experimental quantum compressed sensing for a seven-qubit system
• Introduction to Haar Measure Tools in Quantum Information: A Beginner's Tutorial
• Unsupervised phase discovery with deep anomaly detection
• Quantum Tomography Protocols with Positivity are Compressed Sensing Protocols
• Machine learning assisted quantum state estimation
• Unsupervised machine learning of topological phase transitions from experimental data
• Efficient quantum state tomography with convolutional neural networks
• Out-of-distribution generalization for learning quantum dynamics
• Precise measurement of quantum observables with neural-network estimators
• Attention-based Quantum Tomography
• Neural Error Mitigation of Near-Term Quantum Simulations
• Neural-network quantum state tomography
• A Scalable Maximum Likelihood Method for Quantum State Tomography
• Practical adaptive quantum tomography
• Projected Least-Squares Quantum Process Tomography
• Variational Quantum Anomaly Detection: Unsupervised mapping of phase diagrams on a physical quantum computer
• Inferring pointwise diffusion properties of single trajectories with deep learning
• Quantum readout error mitigation via deep learning
• Flexible learning of quantum states with generative query neural networks
• Independent State and Measurement Characterization for Quantum Computers
• Efficient Quantum State Sample Tomography with Basis-dependent Neural-networks
• Adaptive Quantum State Tomography with Active Learning
• Certification of quantum states with hidden structure of their bitstrings
• Enhancing quantum state tomography via resource-efficient attention-based neural networks
• Empirical Sample Complexity of Neural Network Mixed State Reconstruction
• Certification of quantum state functions under partial information
• Out-of-distribution generalisation for learning quantum channels with low-energy coherent states