Machine learning enables completely automatic tuning of a quantum device faster than human experts

Abstract

Device variability is a bottleneck for the scalability of semiconductor quantum devices. Increasing device control comes at the cost of a large parameter space that has to be explored in order to find the optimal operating conditions. We demonstrate a statistical tuning algorithm that navigates this entire parameter space, using just a few modelling assumptions, in the search for specific electron transport features. We focused on gate-defined quantum dot devices, demonstrating fully automated tuning of two different devices to double quantum dot regimes in an up to eight-dimensional gate voltage space. We considered a parameter space defined by the maximum range of each gate voltage in these devices, demonstrating expected tuning in under 70 minutes. This performance exceeded a human benchmark, although we recognise that there is room for improvement in the performance of both humans and machines. Our approach is approximately 180 times faster than a pure random search of the parameter space, and it is readily applicable to different material systems and device architectures. With an efficient navigation of the gate voltage space we are able to give a quantitative measurement of device variability, from one device to another and after a thermal cycle of a device. This is a key demonstration of the use of machine learning techniques to explore and optimise the parameter space of quantum devices and overcome the challenge of device variability.

References in corpus (20)

• Point-Set Registration: Coherent Point Drift
• Interfacing spin qubits in quantum dots and donors - hot, dense and coherent
• Quantum simulation of a Fermi-Hubbard model using a semiconductor quantum dot array
• Quantum dot self consistent electronic structure and the Coulomb blockade
• Loading a quantum-dot based "Qubyte" register
• Notch filtering the nuclear environment of a spin qubit
• Machine Learning techniques for state recognition and auto-tuning in quantum dots
• Auto-tuning of double dot devices in situ with machine learning
• Automated tuning of inter-dot tunnel couplings in quantum dot arrays
• Automated tuning of double quantum dots into specific charge states using neural networks
• Hyperfine-phonon spin relaxation in a single-electron GaAs quantum dot
• Computer-automated tuning of semiconductor double quantum dots into the single-electron regime
• Efficiently measuring a quantum device using machine learning
• Computer-automated tuning procedures for semiconductor quantum dot arrays
• Autonomous tuning and charge state detection of gate defined quantum dots
• Tuning methods for semiconductor spin--qubits
• A Machine Learning Approach for Automated Fine-Tuning of Semiconductor Spin Qubits
• Quantum device fine-tuning using unsupervised embedding learning
• Spectroscopy of Quantum-Dot Orbitals with In-Plane Magnetic Fields
• Orbital effects of a strong in-plane magnetic field on a gate-defined quantum dot

Cited by in corpus (48)

• On scientific understanding with artificial intelligence
• Scaling silicon-based quantum computing using CMOS technology: State-of-the-art, Challenges and Perspectives
• A singlet triplet hole spin qubit in planar Ge
• Probing quantum devices with radio-frequency reflectometry
• Colloquium: Advances in automation of quantum dot devices control
• Simultaneous Operations in a Two-Dimensional Array of Singlet-Triplet Qubits
• Deep Reinforcement Learning for Efficient Measurement of Quantum Devices
• Toward Robust Autotuning of Noisy Quantum Dot Devices
• Quantum device fine-tuning using unsupervised embedding learning
• Ray-based framework for state identification in quantum dot devices
• Deep Learning of Quantum Many-Body Dynamics via Random Driving
• Miniaturizing neural networks for charge state autotuning in quantum dots
• Tuning arrays with rays: Physics-informed tuning of quantum dot charge states
• CMOS Quantum Computing: Toward A Quantum Computer System-on-Chip
• Learning-based Calibration of Flux Crosstalk in Transmon Qubit Arrays
• Automated extraction of capacitive coupling for quantum dot systems
• An automated approach for consecutive tuning of quantum dot arrays
• Autonomous estimation of high-dimensional Coulomb diamonds from sparse measurements
• Evolutionary computation for adaptive quantum device design
• Machine learning optimization of Majorana hybrid nanowires
• Bridging the reality gap in quantum devices with physics-aware machine learning
• Machine Learning-Assisted Manipulation and Readout of Molecular Spin Qubits
• Identifying Pauli spin blockade using deep learning
• Data needs and challenges for quantum dot devices automation
• Cross-architecture Tuning of Silicon and SiGe-based Quantum Devices Using Machine Learning
• Modular Autonomous Virtualization System for Two-Dimensional Semiconductor Quantum Dot Arrays
• Qubit-controlled directional edge states in waveguide QED
• Cryogenic Multiplexing with Bottom-Up Nanowires
• Fully autonomous tuning of a spin qubit
• Autonomous Bootstrapping of Quantum Dot Devices
• Theoretical bounds on data requirements for the ray-based classification
• Bidirectional deep learning of polarization transfer in liquid crystals with application to quantum state preparation
• A compact and versatile cryogenic probe station for quantum device testing
• Visual explanations of machine learning model estimating charge states in quantum dots
• Topological gap protocol based machine learning optimization of Majorana hybrid wires
• Leveraging Off-the-Shelf Silicon Chips for Quantum Computing
• Experimental online quantum dots charge autotuning using neural networks
• All rf-based tuning algorithm for quantum devices using machine learning
• Robust quantum dots charge autotuning using neural network uncertainty
• Automated Discovery of Coupled Mode Setups
• Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams
• Automated in situ optimization and disorder mitigation in a quantum device
• Rapid Autotuning of a SiGe Quantum Dot into the Single-Electron Regime with Machine Learning and RF-Reflectometry FPGA-Based Measurements
• Machine-learning-enabled characterization of individual ring resonators in integrated photonic lattices
• Neural network enhanced cross entropy benchmark for monitored circuits
• Bayesian optimization of non-classical optomechanical correlations
• Learning the dynamics of Markovian open quantum systems from experimental data
• QDFlow: A Python package for physics simulations of quantum dot devices