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:2611.03851

High-fidelity quantum gate learning via physics-informed neural networks

Luis Fabra, Cristian E. Susa, Alcides Montoya, Ariel Norambuena

quant-phSubmitted Nov 2, 2026• Announced Nov 4, 2026• 0 citations
arXivHTMLPDF

Abstract

We propose a physics-informed neural network (PINN) approach for high-fidelity quantum gate learning in both one- and two-qubit systems. We train a PINN using the time-dependent Schrödinger equation, where smooth control fields with fixed boundary conditions are obtained by minimizing a loss function that considers model dynamics, gate error, physical constraints, regularization terms, and multiple initial conditions. Training considers pairs of mutually unbiased bases, while independent validation combines Haar-random input states with the average gate fidelity. Unitary simulations yield an average gate infidelity of $8.49\times10^{-8}$ for Hadamard and values between $3.39\times10^{-7}$ and $4.96\times10^{-6}$ for controlled-NOT under $XX$, $YY$, and $ZZ$ interactions. We examine how the learned control fields depend on the coupling, training configuration, and available local fields, including five exchange-type dipolar scenarios. We test the learned control fields under the Lindblad master equation with dephasing and amplitude damping, theoretically reproducing the expected first-order fidelity loss in the weak-dissipation regime. Finally, boundary-adapted Chebyshev expansions represent 139 learned controls with a minimum common count of $K_\ast=24$ coefficients per control for all eleven family-averaged mean squared errors to fall below $10^{-6}$. Separately, square-pulse and Strang propagation at $K=30$ preserve all 31 continuous polynomial references within infidelity $10^{-5}$ at $N=128$ and all larger tested resolutions, under both sampling rules. These results connect multi-state gate synthesis, control-resource characterization, and compact square-pulse playback.

AI Summary

The paper studies physics-informed neural networks (PINNs) for synthesizing smooth Hadamard and CNOT control pulses in one- and two-qubit Hamiltonians. A network jointly represents density-matrix trajectories for multiple input states and shared control fields. Training uses pairs of mutually unbiased bases, dynamical residuals, target-state errors, trace constraints, and weight regularization. An analytic envelope enforces zero pulse amplitude and first derivative at both endpoints. Independent propagation and average gate fidelity, cross-checked against Haar-random inputs, give unitary infidelities of $8.49\times10^{-8}$ for Hadamard and $3.39\times10^{-7}$, $4.96\times10^{-6}$, and $1.17\times10^{-6}$ for CNOT with $XX$, $YY$, and $ZZ$ interactions. Five exchange-type $XY$ configurations explore different local controls and detunings. A symmetry argument establishes $F_{\mathrm{avg}}\leq2/5$ for specified restricted two-control configurations, independently of pulse shape or duration. Lindblad simulations reuse unitary-trained pulses and reproduce established first-order dissipative fidelity losses; they do not demonstrate decoherence suppression. Boundary-adapted Chebyshev fits compress 139 scalar controls across 31 protocols: 24 coefficients per control suffice for all eleven family-averaged waveform MSEs to fall below $10^{-6}$. Using 30 coefficients, square-pulse and Strang playback preserve every continuous fitted evolution within infidelity $10^{-5}$ at 128 intervals and all larger tested resolutions. The formulation imposes no hard amplitude or bandwidth bounds, and observed control patterns do not establish minimum resources. Waveform MSE does not guarantee gate accuracy; one protocol retains baseline infidelity $1.56\times10^{-3}$. Physical delivery requires device-specific calibration, timing, bandwidth validation, and, for split playback, generator isolation or refocusing.

Little sign of AI-generated textIncrementalSmall numerics onlyMissing comparison

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Comments
22 pages, 18 figures

Related papers

Physics-Informed Neural Networks for Gate Design using Quantum Optimal Control

Sofiia Lauten, Matthew Otten

Implementing quantum gates on quantum computers can require the application of carefully shaped pulses for high-fidelity operations. We explore the use of physics-informed neural networks (PINNs) for quantum optimal control to assess their usefulness in predicting such pulses. Our PINN is a feedforward neural network that utilizes an unsupervised learning approach, whose loss function includes terms that enforce the equations that govern the evolution of a quantum system, measure how close the learned unitary is to the target unitary operation, and ensure state normalization. We use a sinusoidal activation function and adopt variance-type weight initialization, tailored to our activation function. By analyzing the model's performance with important machine learning metrics, we demonstrate that the choice of our architecture is well-suited for this type of problem. We ensure that our network avoids the vanishing and exploding gradients with our relevant choices. We build two different PINNs, one based on the Schrödinger equation and another one based on the Lindblad equation. Our PINNs are able to discover high-fidelity two-qubit gate pulses for a variety of quantum operations, demonstrating its flexibility and robustness. We build two different PINNs, one based on the Schrödinger equation and another one based on the Lindblad equation. Our PINNs are able to discover high-fidelity two-qubit gate pulses for a variety of quantum operations, demonstrating its flexibility and robustness.

quant-pharXiv:2511.09463•Nov 13, 2025•5 citations

Optimal control of stochastic Schrödinger equation via physics informed neural networks: applications in quantum optics

S Vijayaram, Pagavathigounder Balasubramaniam

In this paper, authors present a physics-informed neural networks (PINN) approach for solving the optimal control problem (OCP) of the stochastic Schrödinger equation (SSE), with an emphasis on applications in quantum optics. The SSE models quantum systems under uncertainty, a scenario often encountered in open quantum systems where environmental interactions introduce randomness into the system dynamics. These stochastic dynamics are particularly relevant in quantum optics, where precise control over quantum states is crucial for applications such as quantum computing, secure communication, and measurement protocols. Traditional numerical methods for solving such problems face limitations due to high computational costs and the complexity associated with stochastic partial differential equations. The proposed approach utilises PINN, a type of deep learning model that integrates physical laws directly into the learning process by incorporating loss functions based on governing equations, initial and boundary conditions. The fidelity-based objective function is constructed to achieve the desired quantum state so as to develop an OCP solving algorithm. The proposed work is distinguished between deterministic drift-based training and post-training stochastic validation. Extensive numerical experiments are demonstrated near-unity deterministic fidelity. Further, a systematic architecture study validated that a moderately deep network yielded optimal performance with reduced computational cost. Fidelity dissipation analysis confirmed that the method maintained accuracy even under strong damping. These findings established the PINN as an efficient and physically consistent framework for quantum optimal control in open systems.

The Philosophical Magazine A Journal of Theoretical Experimental and Applied Physics•Jun 2, 2026•0 citations

Performance of Krotov, PRONTO and PINN for optimal control of quantum gates

Martín D. Jiménez, Murilo D. Forlevesi, Emanuel F. de Lima +1 more

Achieving scalable quantum computing demands high-fidelity operations capable of mitigating population leakage into non-computational states. Physics-Informed Neural Networks (PINNs) have recently emerged as a powerful paradigm to unify quantum hardware characterization (inverse problems) and pulse engineering (direct problems), laying the foundational architecture for autonomous quantum processors. However, standard PINN frameworks face severe numerical bottlenecks, such as spectral bias, when attempting to simultaneously solve highly oscillatory multi-level dynamics and optimize continuous control fields under strict global phase constraints. In this work, we propose an enhanced PINN scheme for quantum optimal control (PINNQOC) that circumvents these limitations by incorporating Fourier feature embeddings, dynamic epoch normalization, and an informed pre-training routine. To rigorously evaluate its performance, we systematically benchmark our framework against two premier continuous control solvers: the first-order Krotov method and the second-order Projection Operator Newton Method for Trajectory Optimization (PRONTO). These techniques are applied to implement multiple quantum gates on a truncated three-level fluxonium qubit and a four-level Nitrogen-Vacancy center coupled to a Carbon-13 nuclear spin. Our advanced PINNQOC approach successfully suppresses population leakage while achieving gate fidelities exceeding 99.9$\%$, matching the efficacy of traditional solvers. Finally, we provide a comprehensive analysis of computational times, iteration efficiency, and mean leakage, highlighting the distinct trade-offs and avenues for embedding physics-guided machine learning into automated quantum hardware pipelines.

quant-pharXiv:2607.23276•Jul 28, 2026•1 citation

Physics-Informed Neural Networks for Open Quantum Systems: Modelling, Noise-Aware Simulation and Residual-Based Quantum Control

Salako Najeem Abiodun, Olatinwo Adenike Sola, Olubudo Paul Ajibola

Quantum systems in near-term devices operate in noisy, open-system regimes where decoherence and control imperfections are unavoidable. This study presents a physics-informed neural-network framework for modelling, noiseaware simulation, and residual-based control of open quantum systems, validated against a closed-form Lindblad solution for a driven, amplitude-damped qubit rather than a numerical reference. Across three random seeds, the trained network reproduces population and coherence dynamics with a mean RMSE of 0.00060 and a standard deviation of 0.00054. The mixed-state fidelity exceeds 0.999999 over the evaluation trajectory, while the squared Bloch-vector norm remains within the physical bound for the main modelling benchmark. Removing the Fourier-feature input encoding produces a 70-fold degradation in RMSE, confirming a strong representational benefit for the oscillatory dynamics. Direct comparison against fourth-order Runge-Kutta integration shows the classical solver to be approximately five orders of magnitude faster and two orders more accurate at this scale; the value of the proposed framework for a single qubit therefore lies in data-free, physics-constrained modelling rather than computational speed. A residual-based state-transfer control demonstration and a control-effort sweep further reveal a clear fidelity-versus-energy trade-off and a marked reduction in seed-to-seed variation as regularisation increases. These results support physics-constrained learning as a faithful approach to singlequbit open-system modelling and control, while motivating further validation on multi-qubit systems before broader scalability claims are made.

International Journal of Innovative Science and Research Technology (IJISRT)•Sep 18, 2026•0 citations

Evolution-Level Quantum Optimal Control of Single-Qubit Gates with Physics-Informed Neural Networks

Yao Du, Jian-Jian Cheng, Lin Zhang +2 more

Quantum gate design is often represented as pulse optimization, although the physical object that implements a gate is the full controlled evolution generated by the pulse. Here we use physics-informed neural networks to represent single-qubit gate design at this evolution level: the control fields, the Bloch-state trajectories, and the total duration are learned together under the Bloch equation. This changes the optimized object from pulse amplitudes to a differentiable physical process whose structure can be inspected and refined. For rotation gates, the optimized evolutions recover the physical organization expected for bounded single-qubit control, with no prescribed pulse ansatz or duration scan. For a geometric gate, the representation identifies localized bottlenecks in maintaining the geometric condition and turns this diagnosis into feedback, reducing the residual path error while preserving high fidelity. Thus physics-informed learning is used not only to synthesize gates, but also to make optimized quantum controls physically readable, diagnosable, and locally refinable. This process-level view may be especially useful for adapting gates to hardware-specific, task-specific, and locally varying experimental constraints.

quant-pharXiv:2607.14884•Jul 17, 2026•0 citations

Learning and inverting driven open quantum systems via physics-informed neural networks

Sutirtha Biswas, Emmanuel Paspalakis

Abstract We demonstrate that system-agnostic physics-informed neural networks (PINNs) can efficiently learn the dynamical solution of quantum master equations, as compared to problem-specific numerical solvers, with respect to accuracy, stability of training convergence, robustness towards bath parameters or initial conditions, and equivalent convergence times for the non-Markovian evolution of two-level quantum systems. We study cases of quantum dot systems driven by external electromagnetic fields and coupled to an acoustic phonon environment, and analyze two problem setups, the evolution of Bloch vectorized coupled differential equations obtained from a Lindblad master equation and the evolution of a non-Markovian master equation obtained from the Nakajima–Zwanzig formulation. We implement a fully connected PINN architecture to solve the two problems. We also use the same methodology to solve the inverse problem of estimation of bath parameters in a supervised fashion, but with a very limited number of noisy samples.

Machine Learning Science and Technology•Feb 27, 2026•2 citations
We propose a physics-informed neural network (PINN) approach for high-fidelity quantum gate learning in both one- and two-qubit systems. We train a PINN using the time-dependent Schrödinger equation, where smooth control fields with fixed boundary conditions are obtained by minimizing a loss function that considers model dynamics, gate error, physical constraints, regularization terms, and multiple initial conditions. Training considers pairs of mutually unbiased bases, while independent validation combines Haar-random input states with the average gate fidelity. Unitary simulations yield an average gate infidelity of 8.49×10−88.49\times10^{-8}8.49×10−8 for Hadamard and values between 3.39×10−73.39\times10^{-7}3.39×10−7 and 4.96×10−64.96\times10^{-6}4.96×10−6 for controlled-NOT under XXXXXX, YYYYYY, and ZZZZZZ interactions. We examine how the learned control fields depend on the coupling, training configuration, and available local fields, including five exchange-type dipolar scenarios. We test the learned control fields under the Lindblad master equation with dephasing and amplitude damping, theoretically reproducing the expected first-order fidelity loss in the weak-dissipation regime. Finally, boundary-adapted Chebyshev expansions represent 139 learned controls with a minimum common count of K∗=24K_\ast=24K∗​=24 coefficients per control for all eleven family-averaged mean squared errors to fall below 10−610^{-6}10−6. Separately, square-pulse and Strang propagation at K=30K=30K=30 preserve all 31 continuous polynomial references within infidelity 10−510^{-5}10−5 at N=128N=128N=128 and all larger tested resolutions, under both sampling rules. These results connect multi-state gate synthesis, control-resource characterization, and compact square-pulse playback.
The paper studies physics-informed neural networks (PINNs) for synthesizing smooth Hadamard and CNOT control pulses in one- and two-qubit Hamiltonians. A network jointly represents density-matrix trajectories for multiple input states and shared control fields. Training uses pairs of mutually unbiased bases, dynamical residuals, target-state errors, trace constraints, and weight regularization. An analytic envelope enforces zero pulse amplitude and first derivative at both endpoints.
Independent propagation and average gate fidelity, cross-checked against Haar-random inputs, give unitary infidelities of 8.49×10−88.49\times10^{-8}8.49×10−8 for Hadamard and 3.39×10−73.39\times10^{-7}3.39×10−7, 4.96×10−64.96\times10^{-6}4.96×10−6, and 1.17×10−61.17\times10^{-6}1.17×10−6 for CNOT with XXXXXX, YYYYYY, and ZZZZZZ interactions. Five exchange-type XYXYXY configurations explore different local controls and detunings. A symmetry argument establishes Favg≤2/5F_{\mathrm{avg}}\leq2/5Favg​≤2/5 for specified restricted two-control configurations, independently of pulse shape or duration. Lindblad simulations reuse unitary-trained pulses and reproduce established first-order dissipative fidelity losses; they do not demonstrate decoherence suppression.
Boundary-adapted Chebyshev fits compress 139 scalar controls across 31 protocols: 24 coefficients per control suffice for all eleven family-averaged waveform MSEs to fall below 10−610^{-6}10−6. Using 30 coefficients, square-pulse and Strang playback preserve every continuous fitted evolution within infidelity 10−510^{-5}10−5 at 128 intervals and all larger tested resolutions.
The formulation imposes no hard amplitude or bandwidth bounds, and observed control patterns do not establish minimum resources. Waveform MSE does not guarantee gate accuracy; one protocol retains baseline infidelity 1.56×10−31.56\times10^{-3}1.56×10−3. Physical delivery requires device-specific calibration, timing, bandwidth validation, and, for split playback, generator isolation or refocusing.
Implementing quantum gates on quantum computers can require the application of carefully shaped pulses for high-fidelity operations. We explore the use of physics-informed neural networks (PINNs) for quantum optimal control to assess their usefulness in predicting such pulses. Our PINN is a feedforward neural network that utilizes an unsupervised learning approach, whose loss function includes terms that enforce the equations that govern the evolution of a quantum system, measure how close the learned unitary is to the target unitary operation, and ensure state normalization. We use a sinusoidal activation function and adopt variance-type weight initialization, tailored to our activation function. By analyzing the model's performance with important machine learning metrics, we demonstrate that the choice of our architecture is well-suited for this type of problem. We ensure that our network avoids the vanishing and exploding gradients with our relevant choices. We build two different PINNs, one based on the Schrödinger equation and another one based on the Lindblad equation. Our PINNs are able to discover high-fidelity two-qubit gate pulses for a variety of quantum operations, demonstrating its flexibility and robustness. We build two different PINNs, one based on the Schrödinger equation and another one based on the Lindblad equation. Our PINNs are able to discover high-fidelity two-qubit gate pulses for a variety of quantum operations, demonstrating its flexibility and robustness.
In this paper, authors present a physics-informed neural networks (PINN) approach for solving the optimal control problem (OCP) of the stochastic Schrödinger equation (SSE), with an emphasis on applications in quantum optics. The SSE models quantum systems under uncertainty, a scenario often encountered in open quantum systems where environmental interactions introduce randomness into the system dynamics. These stochastic dynamics are particularly relevant in quantum optics, where precise control over quantum states is crucial for applications such as quantum computing, secure communication, and measurement protocols. Traditional numerical methods for solving such problems face limitations due to high computational costs and the complexity associated with stochastic partial differential equations. The proposed approach utilises PINN, a type of deep learning model that integrates physical laws directly into the learning process by incorporating loss functions based on governing equations, initial and boundary conditions. The fidelity-based objective function is constructed to achieve the desired quantum state so as to develop an OCP solving algorithm. The proposed work is distinguished between deterministic drift-based training and post-training stochastic validation. Extensive numerical experiments are demonstrated near-unity deterministic fidelity. Further, a systematic architecture study validated that a moderately deep network yielded optimal performance with reduced computational cost. Fidelity dissipation analysis confirmed that the method maintained accuracy even under strong damping. These findings established the PINN as an efficient and physically consistent framework for quantum optimal control in open systems.
Achieving scalable quantum computing demands high-fidelity operations capable of mitigating population leakage into non-computational states. Physics-Informed Neural Networks (PINNs) have recently emerged as a powerful paradigm to unify quantum hardware characterization (inverse problems) and pulse engineering (direct problems), laying the foundational architecture for autonomous quantum processors. However, standard PINN frameworks face severe numerical bottlenecks, such as spectral bias, when attempting to simultaneously solve highly oscillatory multi-level dynamics and optimize continuous control fields under strict global phase constraints. In this work, we propose an enhanced PINN scheme for quantum optimal control (PINNQOC) that circumvents these limitations by incorporating Fourier feature embeddings, dynamic epoch normalization, and an informed pre-training routine. To rigorously evaluate its performance, we systematically benchmark our framework against two premier continuous control solvers: the first-order Krotov method and the second-order Projection Operator Newton Method for Trajectory Optimization (PRONTO). These techniques are applied to implement multiple quantum gates on a truncated three-level fluxonium qubit and a four-level Nitrogen-Vacancy center coupled to a Carbon-13 nuclear spin. Our advanced PINNQOC approach successfully suppresses population leakage while achieving gate fidelities exceeding 99.9%\%%, matching the efficacy of traditional solvers. Finally, we provide a comprehensive analysis of computational times, iteration efficiency, and mean leakage, highlighting the distinct trade-offs and avenues for embedding physics-guided machine learning into automated quantum hardware pipelines.
Quantum systems in near-term devices operate in noisy, open-system regimes where decoherence and control imperfections are unavoidable. This study presents a physics-informed neural-network framework for modelling, noiseaware simulation, and residual-based control of open quantum systems, validated against a closed-form Lindblad solution for a driven, amplitude-damped qubit rather than a numerical reference. Across three random seeds, the trained network reproduces population and coherence dynamics with a mean RMSE of 0.00060 and a standard deviation of 0.00054. The mixed-state fidelity exceeds 0.999999 over the evaluation trajectory, while the squared Bloch-vector norm remains within the physical bound for the main modelling benchmark. Removing the Fourier-feature input encoding produces a 70-fold degradation in RMSE, confirming a strong representational benefit for the oscillatory dynamics. Direct comparison against fourth-order Runge-Kutta integration shows the classical solver to be approximately five orders of magnitude faster and two orders more accurate at this scale; the value of the proposed framework for a single qubit therefore lies in data-free, physics-constrained modelling rather than computational speed. A residual-based state-transfer control demonstration and a control-effort sweep further reveal a clear fidelity-versus-energy trade-off and a marked reduction in seed-to-seed variation as regularisation increases. These results support physics-constrained learning as a faithful approach to singlequbit open-system modelling and control, while motivating further validation on multi-qubit systems before broader scalability claims are made.
Quantum gate design is often represented as pulse optimization, although the physical object that implements a gate is the full controlled evolution generated by the pulse. Here we use physics-informed neural networks to represent single-qubit gate design at this evolution level: the control fields, the Bloch-state trajectories, and the total duration are learned together under the Bloch equation. This changes the optimized object from pulse amplitudes to a differentiable physical process whose structure can be inspected and refined. For rotation gates, the optimized evolutions recover the physical organization expected for bounded single-qubit control, with no prescribed pulse ansatz or duration scan. For a geometric gate, the representation identifies localized bottlenecks in maintaining the geometric condition and turns this diagnosis into feedback, reducing the residual path error while preserving high fidelity. Thus physics-informed learning is used not only to synthesize gates, but also to make optimized quantum controls physically readable, diagnosable, and locally refinable. This process-level view may be especially useful for adapting gates to hardware-specific, task-specific, and locally varying experimental constraints.
Abstract We demonstrate that system-agnostic physics-informed neural networks (PINNs) can efficiently learn the dynamical solution of quantum master equations, as compared to problem-specific numerical solvers, with respect to accuracy, stability of training convergence, robustness towards bath parameters or initial conditions, and equivalent convergence times for the non-Markovian evolution of two-level quantum systems. We study cases of quantum dot systems driven by external electromagnetic fields and coupled to an acoustic phonon environment, and analyze two problem setups, the evolution of Bloch vectorized coupled differential equations obtained from a Lindblad master equation and the evolution of a non-Markovian master equation obtained from the Nakajima–Zwanzig formulation. We implement a fully connected PINN architecture to solve the two problems. We also use the same methodology to solve the inverse problem of estimation of bath parameters in a supervised fashion, but with a very limited number of noisy samples.