Efficiently measuring a quantum device using machine learning

Abstract

Scalable quantum technologies will present challenges for characterizing and tuning quantum devices. This is a time-consuming activity, and as the size of quantum systems increases, this task will become intractable without the aid of automation. We present measurements on a quantum dot device performed by a machine learning algorithm. The algorithm selects the most informative measurements to perform next using information theory and a probabilistic deep-generative model, the latter capable of generating multiple full-resolution reconstructions from scattered partial measurements. We demonstrate, for two different measurement configurations, that the algorithm outperforms standard grid scan techniques, reducing the number of measurements required by up to 4 times and the measurement time by 3.7 times. Our contribution goes beyond the use of machine learning for data search and analysis, and instead presents the use of algorithms to automate measurement. This work lays the foundation for automated control of large quantum circuits.

References in corpus (10)

• Automatic chemical design using a data-driven continuous representation of molecules
• Spins in few-electron quantum dots
• Interfacing spin qubits in quantum dots and donors - hot, dense and coherent
• Loading a quantum-dot based "Qubyte" register
• Fast charge sensing of a cavity-coupled double quantum dot using a Josephson parametric amplifier
• Machine Learning techniques for state recognition and auto-tuning in quantum dots
• Automated tuning of inter-dot tunnel couplings in quantum dot arrays
• Computer-automated tuning of semiconductor double quantum dots into the single-electron regime
• A Machine Learning Approach for Automated Fine-Tuning of Semiconductor Spin Qubits
• Compressed Optimization of Device Architectures (CODA) for semiconductor quantum devices

Cited by in corpus (35)

• Artificial Intelligence and Machine Learning for Quantum Technologies
• Machine learning enables completely automatic tuning of a quantum device faster than human experts
• Auto-tuning of double dot devices in situ with machine learning
• Shadow epitaxy for in-situ growth of generic semiconductor/superconductor devices
• Deep Reinforcement Learning for Quantum State Preparation with Weak Nonlinear Measurements
• Autonomous tuning and charge state detection of gate defined quantum dots
• Benchmark and application of unsupervised classification approaches for univariate data
• Deep Reinforcement Learning for Efficient Measurement of Quantum Devices
• Quantum device fine-tuning using unsupervised embedding learning
• Machine Learning and Quantum Devices
• Modeling and Control of a Reconfigurable Photonic Circuit using Deep Learning
• Integration of spectator qubits into quantum computer architectures for hardware tuneup and calibration
• Learning-based Calibration of Flux Crosstalk in Transmon Qubit Arrays
• An automated approach for consecutive tuning of quantum dot arrays
• Autonomous estimation of high-dimensional Coulomb diamonds from sparse measurements
• Robust and fast post-processing of single-shot spin qubit detection events with a neural network
• Extending qubit coherence by adaptive quantum environment learning
• Machine learning optimization of Majorana hybrid nanowires
• Retrieving past quantum features with deep hybrid classical-quantum reservoir computing
• Machine Learning-Assisted Manipulation and Readout of Molecular Spin Qubits
• Neural networks for quantum state tomography with constrained measurements
• Real-time adaptive estimation of decoherence timescales for a single qubit
• Visual explanations of machine learning model estimating charge states in quantum dots
• A compact and versatile cryogenic probe station for quantum device testing
• Topological gap protocol based machine learning optimization of Majorana hybrid wires
• Simulation of Charge Stability Diagrams for Automated Tuning Solutions (SimCATS)
• On Noise-Sensitive Automatic Tuning of Gate-Defined Sensor Dots
• Fast characterization of multiplexed single-electron pumps with machine learning
• Automated Discovery of Coupled Mode Setups
• Adaptive filtering of projective quantum measurements using discrete stochastic methods
• Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams
• QDsim: A user-friendly toolbox for simulating large-scale quantum dot devices
• Automatic detection of single-electron regime of quantum dots and definition of virtual gates using U-Net and clustering
• Rapid Autotuning of a SiGe Quantum Dot into the Single-Electron Regime with Machine Learning and RF-Reflectometry FPGA-Based Measurements
• Neural Network Based Qubit Environment Characterization