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:2201.08770 · Physical Review Applied

Generalization metrics for practical quantum advantage in generative models

Kaitlin Gili, Marta Mauri, Alejandro Perdomo‐Ortiz

Published Apr 17, 2024• 11 citations
arXivHTMLPDF

Abstract

As the quantum computing community gravitates towards understanding the practical benefits of quantum computers, having a clear definition and evaluation scheme for assessing practical quantum advantage in the context of specific applications is paramount. Generative modeling, for example, is a widely accepted natural use case for quantum computers, and yet has lacked a concrete approach for quantifying success of quantum models over classical ones. In this work, we construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Using the sample-based approach proposed here, any generative model, from state-of-the-art classical generative models such as generative adversarial networks (GANs) to quantum models such as quantum circuit born machines, can be evaluated under the same conditions on a concrete well-defined framework. In contrast to other sample-based metrics for probing practical generalization, we leverage constrained optimization problems (e.g., cardinality-constrained problems) and use these discrete datasets to define specific metrics capable of unambiguously measuring the quality of the samples and the model's generalization capabilities for generating data beyond the training set, but still within the valid solution space. Additionally, our metrics can diagnose trainability issues such as mode collapse and overfitting, as we illustrate when comparing GANs to quantum-inspired models built out of tensor networks. Our simulation results show that our quantum-inspired models have up to a 68 times enhancement in generating unseen unique and valid samples compared to the GANs explored here, and a ratio of 61:2 for generating samples with better quality than those observed in the training set. We foresee these metrics as valuable tools for rigorously defining practical quantum advantage in the domain of generative modeling, where finding a winning model remains an ongoing challenge as new architectures are developed.

DOI
10.1103/physrevapplied.21.044032

Related papers

A framework for demonstrating practical quantum advantage: comparing quantum against classical generative models

Mohamed Hibat-Allah, Marta Mauri, Juan Carrasquilla +1 more

Abstract Generative modeling has seen a rising interest in both classical and quantum machine learning, and it represents a promising candidate to obtain a practical quantum advantage in the near term. In this study, we build over an existing framework for evaluating the generalization performance of generative models, and we establish the first quantitative comparative race towards practical quantum advantage (PQA) between classical and quantum generative models, namely Quantum Circuit Born Machines (QCBMs), Transformers (TFs), Recurrent Neural Networks (RNNs), Variational Autoencoders (VAEs), and Wasserstein Generative Adversarial Networks (WGANs). After defining four types of PQAs scenarios, we focus on what we refer to as potential PQA, aiming to compare quantum models with the best-known classical algorithms for the task at hand. We let the models race on a well-defined and application-relevant competition setting, where we illustrate and demonstrate our framework on 20 variables (qubits) generative modeling task. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models. Such a feature is highly desirable in a wide range of real-world applications where the available data is scarce.

arXiv:2303.15626•Communications Physics•Feb 28, 2024•41 citations

Do quantum circuit Born machines generalize?

Kaitlin Gili, Mohamed Hibat-Allah, Marta Mauri +2 more

Abstract In recent proposals of quantum circuit models for generative tasks, the discussion about their performance has been limited to their ability to reproduce a known target distribution. For example, expressive model families such as quantum circuit Born machines (QCBMs) have been almost entirely evaluated on their capability to learn a given target distribution with high accuracy. While this aspect may be ideal for some tasks, it limits the scope of a generative model’s assessment to its ability to memorize data rather than generalize . As a result, there has been little understanding of a model’s generalization performance and the relation between such capability and the resource requirements, e.g. the circuit depth and the amount of training data. In this work, we leverage upon a recently proposed generalization evaluation framework to begin addressing this knowledge gap. We first investigate the QCBM’s learning process of a cardinality-constrained distribution and see an increase in generalization performance while increasing the circuit depth. In the 12-qubit example presented here, we observe that with as few as 30 % of the valid data in the training set, the QCBM exhibits the best generalization performance toward generating unseen and valid data. Lastly, we assess the QCBM’s ability to generalize not only to valid samples, but to high-quality bitstrings distributed according to an adequately re-weighted distribution. We see that the QCBM is able to effectively learn the reweighted dataset and generate unseen samples with higher quality than those in the training set. To the best of our knowledge, this is the first work in the literature that presents the QCBM’s generalization performance as an integral evaluation metric for quantum generative models, and demonstrates the QCBM’s ability to generalize to high-quality, desired novel samples.

arXiv:2207.13645•Quantum Science and Technology•May 15, 2023•30 citations

"Train classical, deploy quantum" requires rethinking generalization

Snehal Raj, Natansh Mathur, Alejandro Perdomo-Ortiz

Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum generative models are considered one of the most promising applications for quantum computers, since a quantum circuit naturally produces samples from the distribution it encodes, and for suitable circuits that distribution is believed to be hard for any classical computer to reproduce. A leading strategy trains these models on a classical computer and reserves the quantum device for generating samples at deployment. This is possible when the training loss can be evaluated on a classical computer. A prime example is the maximum mean discrepancy (MMD$^2$), a moment-matching loss that compares the model and the data through their Pauli-$Z$ correlations. Research so far has asked whether such models can be trained and whether their sampling is hard; whether minimizing such an objective yields a model that \emph{generalizes}, rather than one that merely reproduces the training statistics, remains poorly understood. We benchmark thirteen quantum and classical generative models by direct sampling on two application-inspired datasets: first a cardinality-constrained dataset at up to $30$ qubits and second a dataset of genomic single-nucleotide variants, whose valid set is the observed data. Models that converge the loss to the same value differ widely in how much of the unseen valid set they cover. These results indicate that a converged moment-matching loss is not a reliable measure of generalization, and that a train-classical, deploy-quantum workflow has to measure generalization by sampling the trained model, a step that at the sizes of interest is believed to require the quantum device.

quant-pharXiv:2608.31117•Sep 1, 2026•0 citations

Generative adversarial networks in the quantum realm: Computational insights, implementation difficulties, and analytical benchmarks

A. Lumini C Manna, Rajat Subhra Goswami

Abstract Generative Adversarial Networks (GANs) have revolutionized Deep learning-based generative models are still challenging to train. This is due to issues such as mode collapse, instability, and non-convergence. This article provides a comprehensive analysis of the challenges faced by classical GANs, offering insights into their computational flow and limitations. Additionally, it explores Quantum Generative Adversarial Networks (QuGANs), detailing their unique architecture and the mechanism of quantum information generation. To further advance the field, this work presents an in-depth analysis of a hybridized model combining classical GANs and QuGANs, leveraging the strengths of both paradigms to enhance learning and stability. Furthermore, a novel algorithm for training quantum–classical GANs is proposed, with a detailed complexity analysis to assess its computational efficiency. The integration of quantum principles into classical frameworks offers a promising direction to mitigate existing GANs limitations while unlocking new possibilities for quantum machine learning. The proposed approach aims to bridge the gap between classical and quantum generative models, improving training dynamics and sample quality. The objective of this investigation is to establish a foundation for improving the efficiency and comprehension of hybrid GANs architectures, which will allow the design of more efficient and durable generative models in quantum computing.

Engineering Research Express•Dec 4, 2025•1 citation

Enhancing Combinatorial Optimization with Quantum Generative Models

Javier A. Alcazar, Alejandro Perdomo‐Ortiz

Combinatorial optimization is one of the key candidates in the race for practical quantum advantage. In this work, we introduce a new family of quantum-enhanced optimizers and demonstrate how quantum machine learning models known as quantum generative models can find lower minima than those found by means of stand-alone state-of-the-art classical solvers. We present two new quantum-enhanced optimization strategies. The first scheme leverages data points evaluated during the optimization search from any quantum or classical optimizer. In this scheme, we show how our quantum generative model boosts the performance of classical solvers in hard-to-solve instances where the classical solver is not capable of making progress as a stand-alone strategy. The second quantum optimization strategy works as a stand-alone solver. Here we show its superior performance when the goal is to find the best minimum within the least number of cost function evaluations. Under this setting, we benchmark our quantum-enhanced optimization strategies against several solvers, including Bayesian optimizers which are known to be one of the best competing solvers in such tasks. To illustrate our findings, these benchmarks are performed in the context of the portfolio optimization problem by constructing instances from the S&P 500 stock market index. We show that our quantum-inspired generative models based on tensor networks generalize to unseen candidates with lower cost function values than any of the candidates seen by the classical solvers. This is the first demonstration of the generalization capabilities of quantum generative models that brings real value in the context of an industrial-scale application.

•Jan 15, 2021•4 citations

Application of quantum-inspired generative models to small molecular datasets

Charles Moussa, Hao Wang, Mauricio Araya‐Polo +2 more

Quantum and quantum-inspired machine learning has emerged as a promising and challenging research field due to the increased popularity of quantum computing, especially with near-term devices. Theoretical contributions point toward generative modeling as a promising direction to realize the first examples of real-world quantum advantages from these technologies. A few empirical studies also demonstrate such potential, especially when considering quantum-inspired models based on tensor networks. In this work, we apply tensor-network-based generative models to the problem of molecular discovery. In our approach, we utilize two small molecular datasets: a subset of 4989 molecules from the QM9 dataset and a small in-house dataset of 516 validated antioxidants from TotalEnergies. We compare several tensor network models against a generative adversarial network using different sample-based metrics, which reflect their learning performances on each task, and multiobjective performances using 3 relevant molecular metrics per task. We also combine the output of the models and demonstrate empirically that such a combination can be beneficial, advocating for the unification of classical and quantum(-inspired) generative learning.

arXiv:2304.10867•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 17, 2023•10 citations
As the quantum computing community gravitates towards understanding the practical benefits of quantum computers, having a clear definition and evaluation scheme for assessing practical quantum advantage in the context of specific applications is paramount. Generative modeling, for example, is a widely accepted natural use case for quantum computers, and yet has lacked a concrete approach for quantifying success of quantum models over classical ones. In this work, we construct a simple and unambiguous approach to probe practical quantum advantage for generative modeling by measuring the algorithm's generalization performance. Using the sample-based approach proposed here, any generative model, from state-of-the-art classical generative models such as generative adversarial networks (GANs) to quantum models such as quantum circuit born machines, can be evaluated under the same conditions on a concrete well-defined framework. In contrast to other sample-based metrics for probing practical generalization, we leverage constrained optimization problems (e.g., cardinality-constrained problems) and use these discrete datasets to define specific metrics capable of unambiguously measuring the quality of the samples and the model's generalization capabilities for generating data beyond the training set, but still within the valid solution space. Additionally, our metrics can diagnose trainability issues such as mode collapse and overfitting, as we illustrate when comparing GANs to quantum-inspired models built out of tensor networks. Our simulation results show that our quantum-inspired models have up to a 68 times enhancement in generating unseen unique and valid samples compared to the GANs explored here, and a ratio of 61:2 for generating samples with better quality than those observed in the training set. We foresee these metrics as valuable tools for rigorously defining practical quantum advantage in the domain of generative modeling, where finding a winning model remains an ongoing challenge as new architectures are developed.
Abstract Generative modeling has seen a rising interest in both classical and quantum machine learning, and it represents a promising candidate to obtain a practical quantum advantage in the near term. In this study, we build over an existing framework for evaluating the generalization performance of generative models, and we establish the first quantitative comparative race towards practical quantum advantage (PQA) between classical and quantum generative models, namely Quantum Circuit Born Machines (QCBMs), Transformers (TFs), Recurrent Neural Networks (RNNs), Variational Autoencoders (VAEs), and Wasserstein Generative Adversarial Networks (WGANs). After defining four types of PQAs scenarios, we focus on what we refer to as potential PQA, aiming to compare quantum models with the best-known classical algorithms for the task at hand. We let the models race on a well-defined and application-relevant competition setting, where we illustrate and demonstrate our framework on 20 variables (qubits) generative modeling task. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models. Such a feature is highly desirable in a wide range of real-world applications where the available data is scarce.
Abstract In recent proposals of quantum circuit models for generative tasks, the discussion about their performance has been limited to their ability to reproduce a known target distribution. For example, expressive model families such as quantum circuit Born machines (QCBMs) have been almost entirely evaluated on their capability to learn a given target distribution with high accuracy. While this aspect may be ideal for some tasks, it limits the scope of a generative model’s assessment to its ability to memorize data rather than generalize . As a result, there has been little understanding of a model’s generalization performance and the relation between such capability and the resource requirements, e.g. the circuit depth and the amount of training data. In this work, we leverage upon a recently proposed generalization evaluation framework to begin addressing this knowledge gap. We first investigate the QCBM’s learning process of a cardinality-constrained distribution and see an increase in generalization performance while increasing the circuit depth. In the 12-qubit example presented here, we observe that with as few as 30 % of the valid data in the training set, the QCBM exhibits the best generalization performance toward generating unseen and valid data. Lastly, we assess the QCBM’s ability to generalize not only to valid samples, but to high-quality bitstrings distributed according to an adequately re-weighted distribution. We see that the QCBM is able to effectively learn the reweighted dataset and generate unseen samples with higher quality than those in the training set. To the best of our knowledge, this is the first work in the literature that presents the QCBM’s generalization performance as an integral evaluation metric for quantum generative models, and demonstrates the QCBM’s ability to generalize to high-quality, desired novel samples.
Generative models have become central across science and industry, from image and text synthesis to the design of molecules and materials. Quantum generative models are considered one of the most promising applications for quantum computers, since a quantum circuit naturally produces samples from the distribution it encodes, and for suitable circuits that distribution is believed to be hard for any classical computer to reproduce. A leading strategy trains these models on a classical computer and reserves the quantum device for generating samples at deployment. This is possible when the training loss can be evaluated on a classical computer. A prime example is the maximum mean discrepancy (MMD2^22), a moment-matching loss that compares the model and the data through their Pauli-ZZZ correlations. Research so far has asked whether such models can be trained and whether their sampling is hard; whether minimizing such an objective yields a model that \emph{generalizes}, rather than one that merely reproduces the training statistics, remains poorly understood. We benchmark thirteen quantum and classical generative models by direct sampling on two application-inspired datasets: first a cardinality-constrained dataset at up to 303030 qubits and second a dataset of genomic single-nucleotide variants, whose valid set is the observed data. Models that converge the loss to the same value differ widely in how much of the unseen valid set they cover. These results indicate that a converged moment-matching loss is not a reliable measure of generalization, and that a train-classical, deploy-quantum workflow has to measure generalization by sampling the trained model, a step that at the sizes of interest is believed to require the quantum device.
Abstract Generative Adversarial Networks (GANs) have revolutionized Deep learning-based generative models are still challenging to train. This is due to issues such as mode collapse, instability, and non-convergence. This article provides a comprehensive analysis of the challenges faced by classical GANs, offering insights into their computational flow and limitations. Additionally, it explores Quantum Generative Adversarial Networks (QuGANs), detailing their unique architecture and the mechanism of quantum information generation. To further advance the field, this work presents an in-depth analysis of a hybridized model combining classical GANs and QuGANs, leveraging the strengths of both paradigms to enhance learning and stability. Furthermore, a novel algorithm for training quantum–classical GANs is proposed, with a detailed complexity analysis to assess its computational efficiency. The integration of quantum principles into classical frameworks offers a promising direction to mitigate existing GANs limitations while unlocking new possibilities for quantum machine learning. The proposed approach aims to bridge the gap between classical and quantum generative models, improving training dynamics and sample quality. The objective of this investigation is to establish a foundation for improving the efficiency and comprehension of hybrid GANs architectures, which will allow the design of more efficient and durable generative models in quantum computing.
Combinatorial optimization is one of the key candidates in the race for practical quantum advantage. In this work, we introduce a new family of quantum-enhanced optimizers and demonstrate how quantum machine learning models known as quantum generative models can find lower minima than those found by means of stand-alone state-of-the-art classical solvers. We present two new quantum-enhanced optimization strategies. The first scheme leverages data points evaluated during the optimization search from any quantum or classical optimizer. In this scheme, we show how our quantum generative model boosts the performance of classical solvers in hard-to-solve instances where the classical solver is not capable of making progress as a stand-alone strategy. The second quantum optimization strategy works as a stand-alone solver. Here we show its superior performance when the goal is to find the best minimum within the least number of cost function evaluations. Under this setting, we benchmark our quantum-enhanced optimization strategies against several solvers, including Bayesian optimizers which are known to be one of the best competing solvers in such tasks. To illustrate our findings, these benchmarks are performed in the context of the portfolio optimization problem by constructing instances from the S&P 500 stock market index. We show that our quantum-inspired generative models based on tensor networks generalize to unseen candidates with lower cost function values than any of the candidates seen by the classical solvers. This is the first demonstration of the generalization capabilities of quantum generative models that brings real value in the context of an industrial-scale application.
Quantum and quantum-inspired machine learning has emerged as a promising and challenging research field due to the increased popularity of quantum computing, especially with near-term devices. Theoretical contributions point toward generative modeling as a promising direction to realize the first examples of real-world quantum advantages from these technologies. A few empirical studies also demonstrate such potential, especially when considering quantum-inspired models based on tensor networks. In this work, we apply tensor-network-based generative models to the problem of molecular discovery. In our approach, we utilize two small molecular datasets: a subset of 4989 molecules from the QM9 dataset and a small in-house dataset of 516 validated antioxidants from TotalEnergies. We compare several tensor network models against a generative adversarial network using different sample-based metrics, which reflect their learning performances on each task, and multiobjective performances using 3 relevant molecular metrics per task. We also combine the output of the models and demonstrate empirically that such a combination can be beneficial, advocating for the unification of classical and quantum(-inspired) generative learning.