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:2511.19364

Neural surrogates for designing gravitational wave detectors

Carlos Ruiz-Gonzalez, Sören Arlt, Sebastian Lehner, Arturs Berzins, Yehonathan Drori, Rana X Adhikari, Johannes Brandstetter, Mario Krenn

cs.LGastro-ph.IMgr-qcquant-phSubmitted Nov 24, 2025• Announced Nov 25, 2025
arXivHTMLPDF

Abstract

Physics simulators are essential in science and engineering, enabling the analysis, control, and design of complex systems. In experimental sciences, they are increasingly used to automate experimental design, often via combinatorial search and optimization. However, as the setups grow more complex, the computational cost of traditional, CPU-based simulators becomes a major limitation. Here, we show how neural surrogate models can significantly reduce reliance on such slow simulators while preserving accuracy. Taking the design of interferometric gravitational wave detectors as a representative example, we train a neural network to surrogate the gravitational wave physics simulator Finesse, which was developed by the LIGO community. Despite that small changes in physical parameters can change the output by orders of magnitudes, the model rapidly predicts the quality and feasibility of candidate designs, allowing an efficient exploration of large design spaces. Our algorithm loops between training the surrogate, inverse designing new experiments, and verifying their properties with the slow simulator for further training. Assisted by auto-differentiation and GPU parallelism, our method proposes high-quality experiments much faster than direct optimization. Solutions that our algorithm finds within hours outperform designs that take five days for the optimizer to reach. Though shown in the context of gravitational wave detectors, our framework is broadly applicable to other domains where simulator bottlenecks hinder optimization and discovery.

Comments
20 pages, 7 figures, 4 tables

Related papers

Polynomial neural surrogates for designing photonic quantum experiments

Rohit Chaurasiya, Xuemei Gu

Physics simulators can support the discovery of quantum experiments by predicting the states generated by experimental configurations. When these simulators are computationally expensive, repeated simulator calls can limit the search for experiments that generate a desired quantum state. Here, we develop a physics-inspired polynomial neural surrogate for PyTheus, a graph-based quantum-optics simulator, to predict quantum states and use it to design quantum experiments. Its polynomial activations are motivated by the relation between graph perfect matchings and the resulting state amplitudes. We train separate surrogate models for four-, six-, and eight-photon systems and show that they achieve higher prediction accuracy with fewer trainable parameters than standard multilayer perceptrons. We then use the trained surrogates for inverse design of GHZ, W, and linear-cluster states. For the larger systems, the surrogates also enable faster inverse design than direct optimization with PyTheus. These results suggest that incorporating the underlying physics into neural surrogates can provide an efficient approach to quantum experiment design.

quant-pharXiv:2610.06032•Oct 6, 2026•0 citations

Neural networks as low-cost surrogates for impurity solvers in quantum embedding methods

Rohan Nain, Philip M. Dee, Kipton M. Barros +2 more

A promising application of machine learning is the creation of low-cost surrogate models to mitigate computational bottlenecks in quantum many-body simulations. Here, we explore whether a neural network (NN) can be trained in the low-data regime, with one to two orders of magnitude fewer training examples than previous works, as an efficient substitute for the impurity solver in dynamical mean-field theory simulations of correlated electron models. We show that the NN solver achieves accuracy comparable to popular continuous-time quantum Monte Carlo (CT-QMC) impurity solvers when interpolating between samples within the training set. While the NN's performance decreases notably when extrapolating to lower temperatures outside the training distribution, its output still provides an excellent initial guess for input to more accurate CT-QMC impurity solvers, thus accelerating the time to solution up to a factor of five. We discuss our results in the context of rapid phase-space exploration.

arXiv:2603.25557•Physical review. B./Physical review. B•Aug 31, 2026•0 citations

Physics-inspired Machine Learning for Quantum Error Mitigation

Xiaoyue Xu, Xue, Xin, Tianyu Chen +5 more

Noise is a major obstacle in current quantum computing, and Machine Learning for Quantum Error Mitigation (ML-QEM) promises to address this challenge, enhancing computational accuracy while reducing the sampling overheads of standard QEM methods. Yet, existing models lack physical interpretability and rely heavily on extensive datasets, hindering their scalability in large-scale quantum circuits. To tackle these issues, we introduce the Neural Noise Accumulation Surrogate (NNAS), a physics-inspired neural network for ML-QEM that incorporates the structural characteristics of quantum noise accumulation within multi-layer circuits, endowing the model with physical interpretability. Experimental results demonstrate that NNAS outperforms current methods across a spectrum of metrics, including error mitigation capability, quantum resource consumption, and training dataset size. Notably, for deeper circuits where QEM methods typically struggle, NNAS achieves a remarkable reduction of over half in errors. NNAS also demands substantially fewer training data, reducing dataset reliance by at least an order of magnitude, due to its ability to rapidly capture noise accumulation patterns across circuit layers. This work pioneers the integration of quantum process-derived structural characteristics into neural network architectures, broadly enhancing QEM's performance and applicability, and establishes an integrative paradigm that extends to various quantum-inspired neural network architectures.

arXiv:2501.04558•Jan 8, 2025•0 citations

Probabilistic Simulation of Quantum Circuits with Neural Network Approximations

Jincheng Zhang

The simulation of quantum circuits presents a significant bottleneck in the development and understanding of quantum algorithms. Traditional methods relying on the full wave function description quickly become computationally intractable as the number of qubits and circuit depth increases. This work proposes a novel approach utilizing neural networks to approximate the probabilities of measurement outcomes within a quantum circuit. The core idea is to train a neural network to learn the complex dynamics of quantum evolution, thereby enabling efficient simulation with a significantly reduced parameter space. We introduce a framework that maps the quantum circuit to a neural network architecture, allowing for approximate but tractable simulation. The effectiveness of this approach is demonstrated through theoretical analysis and a conceptual implementation strategy, highlighting its potential to unlock the exploration of complex quantum algorithms and accelerate the development of quantum computing. The primary objective is to provide a computationally feasible alternative to traditional simulation techniques, bridging the gap between theoretical quantum algorithm design and practical implementation. The key innovation lies in leveraging the representational power of neural networks to capture the essential correlations inherent in quantum systems.

•Sep 2, 2026•0 citations

Rapid Simulation Framework for Superconducting Qubit Readout System Inverse Design and Optimization

Albert Lu, Hiu Yung Wong

Qubit readout is one of the most important operations in quantum computers. In superconducting quantum computers, the success of readout depends on many parameters and is difficult to optimize due to the high dimensionality of the problem. In this work, a rapid simulation framework that comprises an analytical model, a neural network (NN), and optimizers using the NN as a surrogate model is proposed. The analytical model is calibrated to the experimental result and allows rapid simulations to generate enough data to train NNs. Single and multi-objective optimizations are performed. It is shown that a better solution can be found using the optimizer than human optimization. Moreover, the framework can find designs with out-of-the-training-range parameters.

International Conference on Simulation of Semiconductor Processes and Devices•Sep 24, 2024•1 citation

Surrogate-guided optimization in quantum networks

Luise Prielinger, Álvaro G. Iñesta, Gayane Vardoyan

Abstract When physical architectures become too complex for analytical study, numerical simulation proves essential to investigate quantum network behavior. Although highly informative, these simulations involve intricate numerical functions without known analytical forms, making traditional optimization techniques that assume continuity, differentiability, or convexity inapplicable. We introduce a more efficient computational framework that employs machine learning models as surrogates for the objective function. We demonstrate the effectiveness of our approach by applying it to three well-known optimization problems in quantum networking: allocating quantum memory across multiple nodes, tuning an experimental parameter in every physical link of a quantum entanglement switch, and finding effective protocol configurations in a large asymmetric quantum network. Our algorithm consistently outperforms Simulated Annealing and Bayesian optimization within the allotted time, improving results by up to 29% and 28%, respectively. Our framework will thus allow for more comprehensive quantum network studies, integrating surrogate-assisted optimization with existing quantum network simulators.

arXiv:2407.17195•npj Quantum Information•May 31, 2025•5 citations
Physics simulators are essential in science and engineering, enabling the analysis, control, and design of complex systems. In experimental sciences, they are increasingly used to automate experimental design, often via combinatorial search and optimization. However, as the setups grow more complex, the computational cost of traditional, CPU-based simulators becomes a major limitation. Here, we show how neural surrogate models can significantly reduce reliance on such slow simulators while preserving accuracy. Taking the design of interferometric gravitational wave detectors as a representative example, we train a neural network to surrogate the gravitational wave physics simulator Finesse, which was developed by the LIGO community. Despite that small changes in physical parameters can change the output by orders of magnitudes, the model rapidly predicts the quality and feasibility of candidate designs, allowing an efficient exploration of large design spaces. Our algorithm loops between training the surrogate, inverse designing new experiments, and verifying their properties with the slow simulator for further training. Assisted by auto-differentiation and GPU parallelism, our method proposes high-quality experiments much faster than direct optimization. Solutions that our algorithm finds within hours outperform designs that take five days for the optimizer to reach. Though shown in the context of gravitational wave detectors, our framework is broadly applicable to other domains where simulator bottlenecks hinder optimization and discovery.
Physics simulators can support the discovery of quantum experiments by predicting the states generated by experimental configurations. When these simulators are computationally expensive, repeated simulator calls can limit the search for experiments that generate a desired quantum state. Here, we develop a physics-inspired polynomial neural surrogate for PyTheus, a graph-based quantum-optics simulator, to predict quantum states and use it to design quantum experiments. Its polynomial activations are motivated by the relation between graph perfect matchings and the resulting state amplitudes. We train separate surrogate models for four-, six-, and eight-photon systems and show that they achieve higher prediction accuracy with fewer trainable parameters than standard multilayer perceptrons. We then use the trained surrogates for inverse design of GHZ, W, and linear-cluster states. For the larger systems, the surrogates also enable faster inverse design than direct optimization with PyTheus. These results suggest that incorporating the underlying physics into neural surrogates can provide an efficient approach to quantum experiment design.
A promising application of machine learning is the creation of low-cost surrogate models to mitigate computational bottlenecks in quantum many-body simulations. Here, we explore whether a neural network (NN) can be trained in the low-data regime, with one to two orders of magnitude fewer training examples than previous works, as an efficient substitute for the impurity solver in dynamical mean-field theory simulations of correlated electron models. We show that the NN solver achieves accuracy comparable to popular continuous-time quantum Monte Carlo (CT-QMC) impurity solvers when interpolating between samples within the training set. While the NN's performance decreases notably when extrapolating to lower temperatures outside the training distribution, its output still provides an excellent initial guess for input to more accurate CT-QMC impurity solvers, thus accelerating the time to solution up to a factor of five. We discuss our results in the context of rapid phase-space exploration.
Noise is a major obstacle in current quantum computing, and Machine Learning for Quantum Error Mitigation (ML-QEM) promises to address this challenge, enhancing computational accuracy while reducing the sampling overheads of standard QEM methods. Yet, existing models lack physical interpretability and rely heavily on extensive datasets, hindering their scalability in large-scale quantum circuits. To tackle these issues, we introduce the Neural Noise Accumulation Surrogate (NNAS), a physics-inspired neural network for ML-QEM that incorporates the structural characteristics of quantum noise accumulation within multi-layer circuits, endowing the model with physical interpretability. Experimental results demonstrate that NNAS outperforms current methods across a spectrum of metrics, including error mitigation capability, quantum resource consumption, and training dataset size. Notably, for deeper circuits where QEM methods typically struggle, NNAS achieves a remarkable reduction of over half in errors. NNAS also demands substantially fewer training data, reducing dataset reliance by at least an order of magnitude, due to its ability to rapidly capture noise accumulation patterns across circuit layers. This work pioneers the integration of quantum process-derived structural characteristics into neural network architectures, broadly enhancing QEM's performance and applicability, and establishes an integrative paradigm that extends to various quantum-inspired neural network architectures.
The simulation of quantum circuits presents a significant bottleneck in the development and understanding of quantum algorithms. Traditional methods relying on the full wave function description quickly become computationally intractable as the number of qubits and circuit depth increases. This work proposes a novel approach utilizing neural networks to approximate the probabilities of measurement outcomes within a quantum circuit. The core idea is to train a neural network to learn the complex dynamics of quantum evolution, thereby enabling efficient simulation with a significantly reduced parameter space. We introduce a framework that maps the quantum circuit to a neural network architecture, allowing for approximate but tractable simulation. The effectiveness of this approach is demonstrated through theoretical analysis and a conceptual implementation strategy, highlighting its potential to unlock the exploration of complex quantum algorithms and accelerate the development of quantum computing. The primary objective is to provide a computationally feasible alternative to traditional simulation techniques, bridging the gap between theoretical quantum algorithm design and practical implementation. The key innovation lies in leveraging the representational power of neural networks to capture the essential correlations inherent in quantum systems.
Qubit readout is one of the most important operations in quantum computers. In superconducting quantum computers, the success of readout depends on many parameters and is difficult to optimize due to the high dimensionality of the problem. In this work, a rapid simulation framework that comprises an analytical model, a neural network (NN), and optimizers using the NN as a surrogate model is proposed. The analytical model is calibrated to the experimental result and allows rapid simulations to generate enough data to train NNs. Single and multi-objective optimizations are performed. It is shown that a better solution can be found using the optimizer than human optimization. Moreover, the framework can find designs with out-of-the-training-range parameters.
Abstract When physical architectures become too complex for analytical study, numerical simulation proves essential to investigate quantum network behavior. Although highly informative, these simulations involve intricate numerical functions without known analytical forms, making traditional optimization techniques that assume continuity, differentiability, or convexity inapplicable. We introduce a more efficient computational framework that employs machine learning models as surrogates for the objective function. We demonstrate the effectiveness of our approach by applying it to three well-known optimization problems in quantum networking: allocating quantum memory across multiple nodes, tuning an experimental parameter in every physical link of a quantum entanglement switch, and finding effective protocol configurations in a large asymmetric quantum network. Our algorithm consistently outperforms Simulated Annealing and Bayesian optimization within the allotted time, improving results by up to 29% and 28%, respectively. Our framework will thus allow for more comprehensive quantum network studies, integrating surrogate-assisted optimization with existing quantum network simulators.