Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2509.19537 · IEEE Transactions on Quantum Engineering

Rapid Autotuning of a SiGe Quantum Dot Into the Single-Electron Regime With Machine Learning and RF-Reflectometry FPGA-Based Measurements

Marc-Antoine Roux, Joffrey Rivard, Victor Yon, Alexis Morel, Dominic Leclerc, Claude Rohrbacher, El Bachir Ndiaye, Felice Francesco Tafuri, Brendan Bono, Stefan Kubicek, Roger Loo, Yosuke Shimura, Julien Jussot, Clément Godfrin, Danny Wan, Kristiaan De Greve, Marc‐André Tétrault, Dominique Drouin, Christian Lupien, Michel Pioro-Ladrière, Eva Dupont-Ferrier

Published Jan 1, 2026• 1 citation
arXivHTMLPDF

Abstract

Spin qubits need to operate within a very precise voltage space around charge state transitions to achieve high-fidelity gates. However, the stability diagrams that allow the identification of the desired charge states are long to acquire. Moreover, the voltage space to search for the desired charge state increases quickly with the number of qubits. Therefore, faster stability diagram acquisitions are needed to scale up a spin qubit quantum processor. Currently, most methods focus on more efficient data sampling. Our approach shows a significant speedup by combining measurement speedup and a reduction in the number of measurements needed to tune a quantum dot device. Using an autotuning algorithm based on a neural network and faster measurements by harnessing the FPGA embedded in Keysight's Quantum Engineering Toolkit (QET), the measurement time of stability diagrams has been reduced by a factor of 9.8. This led to an acceleration factor of 2.2 for the total initialization time of a SiGe quantum dot into the single-electron regime, which is limited by the Python code execution.

DOI
10.1109/tqe.2026.3670353

Related papers

Experimental Online Quantum Dots Charge Autotuning Using Neural Networks

Victor Yon, Bastien Galaup, Claude Rohrbacher +11 more

Spin-based semiconductor qubits hold promise for scalable quantum computing, yet they require reliable autonomous calibration procedures. This study presents an experimental demonstration of online single-dot charge autotuning using a convolutional neural network integrated into a closed-loop calibration system. The autotuning algorithm explores the gates' voltage space to localize charge transition lines, thereby isolating the one-electron regime without human intervention. This exploration leverages the model's uncertainty estimation to find the appropriate gate configuration with minimal measurements while reducing the risk of failures. In 20 experimental runs, our method achieved a success rate of 95% in locating the target electron regime, highlighting the robustness of this approach against noise and distribution shifts from the offline training set. Each tuning run lasted an average of 2 h and 9 min, primarily due to the limited speed of the current measurement. This work validates the feasibility of machine-learning-driven real-time charge autotuning for quantum dot devices, advancing the development toward the control of large qubit arrays.

arXiv:2409.20320•Nano Letters•Feb 27, 2025•4 citations

Automated All-RF Tuning for Spin Qubit Readout and Control

Cornelius Carlsson, Jaime Saez-Mollejo, Federico Fedele +5 more

Efficient tuning of spin qubits remains a major bottleneck in scaling semiconductor quantum dot-based quantum processors. A key challenge is the rapid identification of gate voltage regimes suitable for qubit initialisation, control, and readout. Here, we leverage radio-frequency charge sensing to automate spin qubit tuning, achieving a median tuning time of approximately 15 minutes. In a single continuous run, our routine identifies spin qubits at 12 distinct charge transitions in under 17 hours. Beyond tuning, our routine autonomously acquires data revealing the gate-voltage dependence of the exchange interaction, dephasing time, and quality factor -- quantities that vary substantially between charge configurations. These results represent a step change in high-throughput spin qubit tuning and provide a foundation for a systematic and automated exploration of semiconductor quantum circuits.

arXiv:2506.10834•Jun 12, 2025•0 citations

Robust quantum dots charge autotuning using neural network uncertainty

Victor Yon, Bastien Galaup, Claude Rohrbacher +10 more

Abstract This study presents a machine learning-based procedure to automate the charge tuning of semiconductor spin qubits with minimal human intervention, addressing one of the significant challenges in scaling up quantum dot technologies. This method exploits artificial neural networks to identify noisy transition lines in stability diagrams, guiding a robust exploration strategy leveraging neural network uncertainty estimations. Tested across three distinct offline experimental datasets representing different single-quantum-dot technologies, this approach achieves a tuning success rate of over 99% in optimal cases, where more than 10% of the success is directly attributable to uncertainty exploitation. The challenging constraints of small training sets containing high diagram-to-diagram variability allowed us to evaluate the capabilities and limits of the proposed procedure.

arXiv:2406.05175•Machine Learning Science and Technology•Oct 18, 2024•3 citations

Fast tuning, simulation and characterisation of spin qubits devices using machine learning

Barnaby van Straaten

Semiconducting spin quantum devices present a promising avenue for advancing noisy intermediate-scale quantum (NISQ) computers. However, the complexities involved in their tuning and characterisation currently hinder their scaling. This thesis addresses these challenges by harnessing machine-learning-based approaches. Firstly, I used Gaussian processes to develop a fully automatic tuning algorithm that exclusively used radio-frequency measurements taken on millisecond timescales. Secondly, I employed Bayesian optimisation for charge sensor optimisation and automation. Both algorithms were deployed on depletion mode hole-based Ge/SiGe devices; however, they could easily be applied to other architectures. These automated approaches considerably outperformed manual tuning and represent vital building blocks for algorithms to tune larger quantum dot arrays. Next, I developed algorithms to find the ground state charge configuration in the constant capacitance model, which was orders of magnitude faster than its predecessors, permitting the simulation of much larger arrays of sixteen dots. This open-source package can be used to gain insights into the charge stability diagrams of large quantum dot arrays and facilitates further tuning algorithm development. Lastly, I present a novel application of hidden Markov models to identify and separate the state preparation, measurement and spin-flip errors presented by a pair of hot Loss Divincenzo qubits in a Si-MOS device. This approach not only unravels these error sources but also sheds light on their relationship with various parameters, such as electron temperature, thus contributing a vital understanding to the field of quantum computing.

•Jan 1, 2024•0 citations

Towards autonomous time-calibration of large quantum-dot devices: Detection, real-time feedback, and noise spectroscopy

Anantha S. Rao, Barnaby van Straaten, Valentin John +8 more

The performance and scalability of semiconductor quantum-dot (QD) qubits are limited by electrostatic drift and charge noise that shift operating points and destabilize qubit parameters. As systems expand to large one- and two-dimensional arrays, manual recalibration becomes impractical, creating a need for autonomous stabilization frameworks. Here, we introduce a method that uses the full network of charge-transition lines in repeatedly acquired double-quantum-dot charge stability diagrams (CSDs) as a multidimensional probe of the local electrostatic environment. By accurately tracking the motion of selected transitions in time, we detect voltage drifts, identify abrupt charge reconfigurations, and apply compensating updates to maintain stable operating conditions. We demonstrate our approach on a 10-QD device, showing robust stabilization and real-time diagnostic access to dot-specific noise processes. The high acquisition rate of radio-frequency reflectometry CSD measurements also enables time-domain noise spectroscopy, allowing the extraction of noise power spectral densities, the identification of two-level fluctuators, and the analysis of spatial noise correlations across the array. From our analysis, we find that the background noise at 100~$μ$\si{\hertz} is dominated by drift with a power law of $1/f^2$, accompanied by a few dominant two-level fluctuators and an average linear correlation length of $(188 \pm 38)$~\si{\nano\meter} in the device. These capabilities form the basis of a scalable, autonomous calibration and characterization module for QD-based quantum processors, providing essential feedback for long-duration, high-fidelity qubit operations.

cond-mat.mes-hallCross-listedarXiv:2512.24894•Jan 1, 2026•0 citations

Miniaturizing neural networks for charge state autotuning in quantum dots

Stefanie Czischek, Victor Yon, Marc-Antoine Genest +8 more

Abstract A key challenge in scaling quantum computers is the calibration and control of multiple qubits. In solid-state quantum dots (QDs), the gate voltages required to stabilize quantized charges are unique for each individual qubit, resulting in a high-dimensional control parameter space that must be tuned automatically. Machine learning techniques are capable of processing high-dimensional data—provided that an appropriate training set is available—and have been successfully used for autotuning in the past. In this paper, we develop extremely small feed-forward neural networks that can be used to detect charge-state transitions in QD stability diagrams. We demonstrate that these neural networks can be trained on synthetic data produced by computer simulations, and robustly transferred to the task of tuning an experimental device into a desired charge state. The neural networks required for this task are sufficiently small as to enable an implementation in existing memristor crossbar arrays in the near future. This opens up the possibility of miniaturizing powerful control elements on low-power hardware, a significant step towards on-chip autotuning in future QD computers.

arXiv:2101.03181•Machine Learning Science and Technology•Nov 23, 2021•23 citations
Spin qubits need to operate within a very precise voltage space around charge state transitions to achieve high-fidelity gates. However, the stability diagrams that allow the identification of the desired charge states are long to acquire. Moreover, the voltage space to search for the desired charge state increases quickly with the number of qubits. Therefore, faster stability diagram acquisitions are needed to scale up a spin qubit quantum processor. Currently, most methods focus on more efficient data sampling. Our approach shows a significant speedup by combining measurement speedup and a reduction in the number of measurements needed to tune a quantum dot device. Using an autotuning algorithm based on a neural network and faster measurements by harnessing the FPGA embedded in Keysight's Quantum Engineering Toolkit (QET), the measurement time of stability diagrams has been reduced by a factor of 9.8. This led to an acceleration factor of 2.2 for the total initialization time of a SiGe quantum dot into the single-electron regime, which is limited by the Python code execution.
Spin-based semiconductor qubits hold promise for scalable quantum computing, yet they require reliable autonomous calibration procedures. This study presents an experimental demonstration of online single-dot charge autotuning using a convolutional neural network integrated into a closed-loop calibration system. The autotuning algorithm explores the gates' voltage space to localize charge transition lines, thereby isolating the one-electron regime without human intervention. This exploration leverages the model's uncertainty estimation to find the appropriate gate configuration with minimal measurements while reducing the risk of failures. In 20 experimental runs, our method achieved a success rate of 95% in locating the target electron regime, highlighting the robustness of this approach against noise and distribution shifts from the offline training set. Each tuning run lasted an average of 2 h and 9 min, primarily due to the limited speed of the current measurement. This work validates the feasibility of machine-learning-driven real-time charge autotuning for quantum dot devices, advancing the development toward the control of large qubit arrays.
Efficient tuning of spin qubits remains a major bottleneck in scaling semiconductor quantum dot-based quantum processors. A key challenge is the rapid identification of gate voltage regimes suitable for qubit initialisation, control, and readout. Here, we leverage radio-frequency charge sensing to automate spin qubit tuning, achieving a median tuning time of approximately 15 minutes. In a single continuous run, our routine identifies spin qubits at 12 distinct charge transitions in under 17 hours. Beyond tuning, our routine autonomously acquires data revealing the gate-voltage dependence of the exchange interaction, dephasing time, and quality factor -- quantities that vary substantially between charge configurations. These results represent a step change in high-throughput spin qubit tuning and provide a foundation for a systematic and automated exploration of semiconductor quantum circuits.
Abstract This study presents a machine learning-based procedure to automate the charge tuning of semiconductor spin qubits with minimal human intervention, addressing one of the significant challenges in scaling up quantum dot technologies. This method exploits artificial neural networks to identify noisy transition lines in stability diagrams, guiding a robust exploration strategy leveraging neural network uncertainty estimations. Tested across three distinct offline experimental datasets representing different single-quantum-dot technologies, this approach achieves a tuning success rate of over 99% in optimal cases, where more than 10% of the success is directly attributable to uncertainty exploitation. The challenging constraints of small training sets containing high diagram-to-diagram variability allowed us to evaluate the capabilities and limits of the proposed procedure.
Semiconducting spin quantum devices present a promising avenue for advancing noisy intermediate-scale quantum (NISQ) computers. However, the complexities involved in their tuning and characterisation currently hinder their scaling. This thesis addresses these challenges by harnessing machine-learning-based approaches. Firstly, I used Gaussian processes to develop a fully automatic tuning algorithm that exclusively used radio-frequency measurements taken on millisecond timescales. Secondly, I employed Bayesian optimisation for charge sensor optimisation and automation. Both algorithms were deployed on depletion mode hole-based Ge/SiGe devices; however, they could easily be applied to other architectures. These automated approaches considerably outperformed manual tuning and represent vital building blocks for algorithms to tune larger quantum dot arrays. Next, I developed algorithms to find the ground state charge configuration in the constant capacitance model, which was orders of magnitude faster than its predecessors, permitting the simulation of much larger arrays of sixteen dots. This open-source package can be used to gain insights into the charge stability diagrams of large quantum dot arrays and facilitates further tuning algorithm development. Lastly, I present a novel application of hidden Markov models to identify and separate the state preparation, measurement and spin-flip errors presented by a pair of hot Loss Divincenzo qubits in a Si-MOS device. This approach not only unravels these error sources but also sheds light on their relationship with various parameters, such as electron temperature, thus contributing a vital understanding to the field of quantum computing.
The performance and scalability of semiconductor quantum-dot (QD) qubits are limited by electrostatic drift and charge noise that shift operating points and destabilize qubit parameters. As systems expand to large one- and two-dimensional arrays, manual recalibration becomes impractical, creating a need for autonomous stabilization frameworks. Here, we introduce a method that uses the full network of charge-transition lines in repeatedly acquired double-quantum-dot charge stability diagrams (CSDs) as a multidimensional probe of the local electrostatic environment. By accurately tracking the motion of selected transitions in time, we detect voltage drifts, identify abrupt charge reconfigurations, and apply compensating updates to maintain stable operating conditions. We demonstrate our approach on a 10-QD device, showing robust stabilization and real-time diagnostic access to dot-specific noise processes. The high acquisition rate of radio-frequency reflectometry CSD measurements also enables time-domain noise spectroscopy, allowing the extraction of noise power spectral densities, the identification of two-level fluctuators, and the analysis of spatial noise correlations across the array. From our analysis, we find that the background noise at 100~μμμ\si{\hertz} is dominated by drift with a power law of 1/f21/f^21/f2, accompanied by a few dominant two-level fluctuators and an average linear correlation length of (188±38)(188 \pm 38)(188±38)~\si{\nano\meter} in the device. These capabilities form the basis of a scalable, autonomous calibration and characterization module for QD-based quantum processors, providing essential feedback for long-duration, high-fidelity qubit operations.
Abstract A key challenge in scaling quantum computers is the calibration and control of multiple qubits. In solid-state quantum dots (QDs), the gate voltages required to stabilize quantized charges are unique for each individual qubit, resulting in a high-dimensional control parameter space that must be tuned automatically. Machine learning techniques are capable of processing high-dimensional data—provided that an appropriate training set is available—and have been successfully used for autotuning in the past. In this paper, we develop extremely small feed-forward neural networks that can be used to detect charge-state transitions in QD stability diagrams. We demonstrate that these neural networks can be trained on synthetic data produced by computer simulations, and robustly transferred to the task of tuning an experimental device into a desired charge state. The neural networks required for this task are sufficiently small as to enable an implementation in existing memristor crossbar arrays in the near future. This opens up the possibility of miniaturizing powerful control elements on low-power hardware, a significant step towards on-chip autotuning in future QD computers.