Classification and reconstruction of optical quantum states with deep neural networks
arXiv:2012.02185 · doi:10.1103/PhysRevResearch.3.033278
Abstract
We apply deep-neural-network-based techniques to quantum state classification and reconstruction. We demonstrate high classification accuracies and reconstruction fidelities, even in the presence of noise and with little data. Using optical quantum states as examples, we first demonstrate how convolutional neural networks (CNNs) can successfully classify several types of states distorted by, e.g., additive Gaussian noise or photon loss. We further show that a CNN trained on noisy inputs can learn to identify the most important regions in the data, which potentially can reduce the cost of tomography by guiding adaptive data collection. Secondly, we demonstrate reconstruction of quantum-state density matrices using neural networks that incorporate quantum-physics knowledge. The knowledge is implemented as custom neural-network layers that convert outputs from standard feedforward neural networks to valid descriptions of quantum states. Any standard feed-forward neural-network architecture can be adapted for quantum state tomography (QST) with our method. We present further demonstrations of our proposed [arXiv:2008.03240] QST technique with conditional generative adversarial networks (QST-CGAN). We motivate our choice of a learnable loss function within an adversarial framework by demonstrating that the QST-CGAN outperforms, across a range of scenarios, generative networks trained with standard loss functions. For pure states with additive or convolutional Gaussian noise, the QST-CGAN is able to adapt to the noise and reconstruct the underlying state. The QST-CGAN reconstructs states using up to two orders of magnitude fewer iterative steps than a standard iterative maximum likelihood (iMLE) method. Further, the QST-CGAN can reconstruct both pure and mixed states from two orders of magnitude fewer randomly chosen data points than iMLE.
arXiv comment40 pages, 20 figures, 5 tables, code will be available at https://github.com/quantshah/qst-nn
References in corpus (125)
- Auto-Encoding Variational Bayes
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Conditional Generative Adversarial Nets
- TensorFlow: A system for large-scale machine learning
- Quantum Computing in the NISQ era and beyond
- Supplementary information for "Quantum supremacy using a programmable superconducting processor"
- scikit-image: Image processing in Python
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Gaussian Quantum Information
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Language Models are Few-Shot Learners
- An Introduction to Variational Autoencoders
- Supervised learning with quantum enhanced feature spaces
- Machine learning and the physical sciences
- QuTiP 2: A Python framework for the dynamics of open quantum systems
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- QuTiP: An open-source Python framework for the dynamics of open quantum systems
- Encoding a qubit in an oscillator
- Quantum computation over continuous variables
- Continuous-variable optical quantum state tomography
- Quantum state tomography via compressed sensing
- Quantum algorithms: an overview
- Quantum information processing with superconducting circuits: a review
- Many-body quantum state tomography with neural networks
- The Creation and Detection of Deepfakes: A Survey
- Efficient quantum state tomography
- Reconstruction of non-classical cavity field states with snapshots of their decoherence
- Quantum generative adversarial learning
- Observation of quantum state collapse and revival due to the single-photon Kerr effect
- Quantum state estimation
- Direct Fidelity Estimation from Few Pauli Measurements
- Discovering physical concepts with neural networks
- Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
- The Kerr-Cat Qubit: Stabilization, Readout, and Gates
- Quantum error correction of a qubit encoded in grid states of an oscillator
- New class of quantum error-correcting codes for a bosonic mode
- Twisted Light Transmission over 143 kilometers
- Hand-waving and Interpretive Dance: An Introductory Course on Tensor Networks
- Optimal, reliable estimation of quantum states
- Quantum Tomography via Compressed Sensing: Error Bounds, Sample Complexity, and Efficient Estimators
- Qubit-oscillator systems in the ultrastrong-coupling regime and their potential for preparing nonclassical states
- Quantum Computing with Continuous-Variable Clusters
- Maximum-likelihood estimation of the density matrix
- Quantum state discrimination and its applications
- Reconstructing quantum states with generative models
- Iterative maximum-likelihood reconstruction in quantum homodyne tomography
- Active learning machine learns to create new quantum experiments
- Performance and structure of single-mode bosonic codes
- Blueprint for a Scalable Photonic Fault-Tolerant Quantum Computer
- Maximum Likelihood, Minimum Effort
- Efficient tomography of a quantum many-body system
- Permutationally invariant quantum tomography
- Automated Search for new Quantum Experiments
- Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
- Reinforcement Learning with Neural Networks for Quantum Feedback
- Approximating quantum many-body wave-functions using artificial neural networks
- Neural-Network Quantum States, String-Bond States, and Chiral Topological States
- Learning New Physics from a Machine
- A Neural Decoder for Topological Codes
- General Resource Theories in Quantum Mechanics and Beyond: Operational Characterization via Discrimination Tasks
- Diluted maximum-likelihood algorithm for quantum tomography
- Graph Neural Networks in Particle Physics
- Experimental neural network enhanced quantum tomography
- Quantum generative adversarial learning in a superconducting quantum circuit
- Experimental Machine Learning of Quantum States
- Quantum State Tomography via Linear Regression Estimation
- Constructing exact representations of quantum many-body systems with deep neural networks
- TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
- Quantum information processing with bosonic qubits in circuit QED
- Machine Learning for Quantum Matter
- Integrating Neural Networks with a Quantum Simulator for State Reconstruction
- Latent Space Purification via Neural Density Operators
- Machine-learning-assisted correction of correlated qubit errors in a topological code
- Characterizing Quantum Microwave Radiation and its Entanglement with Superconducting Qubits using Linear Detectors
- Speedup for quantum optimal control from automatic differentiation based on graphics processing units
- Permutationally invariant state reconstruction
- Informationally complete measurements and groups representation
- A practical and efficient approach for Bayesian quantum state estimation
- Scalable reconstruction of density matrices
- Superfast maximum likelihood reconstruction for quantum tomography
- Deep Neural Network Probabilistic Decoder for Stabilizer Codes
- Practical Bayesian Tomography
- Quantum Tomography Protocols with Positivity are Compressed Sensing Protocols
- Full reconstruction of a 14-qubit state within four hours
- On integral probability metrics, ϕ-divergences and binary classification
- High-Fidelity Image Generation With Fewer Labels
- Maximally epistemic interpretations of the quantum state and contextuality
- Using a Recurrent Neural Network to Reconstruct Quantum Dynamics of a Superconducting Qubit from Physical Observations
- Gradient-based optimal control of open quantum systems using quantum trajectories and automatic differentiation
- Computer-inspired Quantum Experiments
- Machine learning assisted quantum state estimation
- Neural network quantum state tomography in a two-qubit experiment
- Integrated tool-set for Control, Calibration and Characterization of quantum devices applied to superconducting qubits
- Universal Gate Set for Continuous-Variable Quantum Computation with Microwave Circuits
- Learning hard quantum distributions with variational autoencoders
- Entanglement Classification via Neural Network Quantum States
- Experimental quantum homodyne tomography via machine learning
- Tomographic measurements on superconducting qubit states
- Machine Learning meets Quantum Foundations: A Brief Survey
- Optimal two-qubit tomography based on local and global measurements: Maximal robustness against errors as described by condition numbers
- Classifying the Large Scale Structure of the Universe with Deep Neural Networks
- On the distinguishability of random quantum states
- Adaptive compressive tomography with no a priori information
- Tensor-Network Approach for Quantum Metrology in Many-Body Quantum Systems
- Eigenstate extraction with neural-network tomography
- Approximability of Discriminators Implies Diversity in GANs
- Assessing the significance of fidelity as a figure of merit in quantum state reconstruction of discrete and continuous variable systems
- Quantum learning of coherent states
- Deep Q-learning decoder for depolarizing noise on the toric code
- Mode-Assisted Unsupervised Learning of Restricted Boltzmann Machines
- Quantitative tomography for continuous variable quantum systems
- Wavefunction positivization via automatic differentiation
- Informational completeness of continuous-variable measurements
- Adaptive compressive tomography: a numerical study
- Optimized Tomography of Continuous Variable Systems Using Excitation Counting
- Neural-network approach for identifying nonclassicality from click-counting data
- Optimal quantum-state tomography with known parameters
- Estimating Cosmological Parameters from the Dark Matter Distribution
- Generalized overlap quantum state tomography
- Optimal Bounds between -Divergences and Integral Probability Metrics
- Quadrature Histograms in Maximum Likelihood Quantum State Tomography
- Maximum likelihood quantum state tomography is inadmissible
- Adaptive Bayesian and frequentist data processing for quantum tomography
- Semi-Supervised Learning with IPM-based GANs: an Empirical Study
Cited by in corpus (7)
- Single-preparation unsupervised quantum machine learning: concepts and applications
- Quantum State Tomography with Conditional Generative Adversarial Networks
- Improving application performance with biased distributions of quantum states
- Neural networks in quantum many-body physics: a hands-on tutorial
- Identifying nonclassicality from experimental data using artificial neural networks
- tqix: A toolbox for Quantum in X: Quantum measurement, quantum tomography, quantum metrology, and others
- All-optical neural network quantum state tomography