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:2107.09599

Quantum Bayesian Neural Networks

Noah Berner, Vincent Fortuin, Jonas Landman

Published Jul 20, 2021• 5 citations
arXivHTMLPDF

Abstract

Quantum machine learning promises great speedups over classical algorithms, but it often requires repeated computations to achieve a desired level of accuracy for its point estimates. Bayesian learning focuses more on sampling from posterior distributions than on point estimation, thus it might be more forgiving in the face of additional quantum noise. We propose a quantum algorithm for Bayesian neural network inference, drawing on recent advances in quantum deep learning, and simulate its empirical performance on several tasks. We find that already for small numbers of qubits, our algorithm approximates the true posterior well, while it does not require any repeated computations and thus fully realizes the quantum speedups.

DOI
10.48550/arxiv.2107.09599

Related papers

Bayesian Quantum Neural Networks

Nam Nguyen, Kwang‐Cheng Chen

The astounding acceleration in Artificial Intelligence and Quantum Computing advances naturally gives rise to a line of research, which unrolls the potential advantages of quantum computing on classical Machine Learning tasks, known as Quantum Machine Learning or Quantum Machine Intelligence. The typical objectives are either (1) exploring the potential quantum advantages on classical learning tasks or (2) levering well-established classical ML algorithms to tackle quantum-related problems on Noisy Intermediate-Scale Quantum (NISQ) devices. Along the second research direction, we study Quantum Neural Networks (QNNs) to accomplish the purpose of Bayesian learning. By observing a wide range of studies on QNNs, in which the sole training method is based on frequentist training, we find that Bayesian learning benefits QNNs from two aspects. First, Bayesian-trained models enjoy a high level of generalization due to the prior and posterior distribution usage compared to frequentist training, which will be justified by this paper’s theoretical study of model capacity. Second, Bayesian Inference offers epistemic uncertainty estimation, which merits the decision-making process. It is worth mentioning that frequentist-trained QNNs generally lack this desirable property. Under the Bayesian training procedure, our derived models can be considered a new class of QNNs (called BayesianQNNs) which possesses both desirable properties of Bayesian Inference while maintaining comparable predictive performance as frequentist counterparts. The proposed Bayesian Quantum Neural Networks is justified by empirical evidence from numerical experiments.

IEEE Access•Jan 1, 2022•36 citations

Quantum Bayesian Inference for Statistical Machine Learning

Jincheng Zhang

Quantum Bayesian Inference (QBI) presents a novel approach to statistical machine learning, utilizing the principles of quantum mechanics to enhance the accuracy and robustness of models, particularly when dealing with high-dimensional data and complex Bayesian frameworks. This paper introduces a quantum algorithm designed to efficiently estimate the posterior distribution of parameters in a Bayesian model through the application of quantum superposition and entanglement, aiming to overcome the limitations of classical methods. We explore the potential of this paradigm shift to deliver exponential speedups in inference tasks, offering a compelling path towards more accurate and reliable statistical machine learning algorithms.

•Aug 29, 2026•0 citations

Bayesian machine learning for Boltzmann machine in quantum-enhanced feature spaces

Yusen Wu, Chao‐Hua Yu, Su‐Juan Qin +2 more

Bayesian learning is ubiquitous for implementing classification and regression tasks, however, it is accompanied by computationally intractable limitations when the feature spaces become extremely large. Aiming to solve this problem, we develop a quantum bayesian learning framework of the restricted Boltzmann machine in the quantum-enhanced feature spaces. Our framework provides the encoding phase to map the real data and Boltzmann weight onto the quantum feature spaces and the training phase to learn an optimal inference function. Specifically, the training phase provides a physical quantity to measure the posterior distribution in quantum feature spaces, and this measure is utilized to design the quantum maximum a posterior (QMAP) algorithm and the quantum predictive distribution estimator (QPDE). It is shown that both quantum algorithms achieve exponential speed-up over their classical counterparts. Furthermore, it is interesting to note that our framework can figure out the classical bayesian learning tasks, i.e. processing the classical data and outputting corresponding classical labels. And a simulation, which is performed on an open-source software framework for quantum computing, illustrates that our algorithms show almost the same classification performance compared to their classical counterparts. Noting that the proposed quantum algorithms utilize the shallow circuit, our work is expected to be implemented on the noisy intermediate-scale quantum (NISQ) devices, and is one of the promising candidates to achieve quantum supremacy.

arXiv:1912.10857•Dec 20, 2019•2 citations

Title: Quantum-Enhanced Bayesian Inference for Machine Learning

Jincheng Zhang

Quantum-enhanced Bayesian inference offers a paradigm shift in the field of machine learning, addressing the fundamental limitations of classical Bayesian methods – namely, computational complexity and scalability – when dealing with high-dimensional data. This paper presents a novel quantum-enhanced Bayesian inference algorithm designed to drastically reduce these challenges. We explore the use of quantum annealing and quantum approximate optimization algorithms to efficiently navigate the complex search space of model parameters, leading to significantly improved accuracy and reduced computational costs. This work demonstrates the potential of quantum computing to revolutionize machine learning, particularly within domains characterized by high data complexity and demanding performance requirements. The core mechanism focuses on leveraging quantum phenomena – superposition and entanglement – to accelerate the exploration of parameter space and improve the convergence of inference algorithms. The investigation includes a detailed analysis of the algorithm's performance compared to classical methods, highlighting the benefits of quantum acceleration in specific machine learning tasks.

•Aug 31, 2026•0 citations

Title: Quantum Bayesian Neural Networks for Ensemble Learning

Jincheng Zhang

Quantum Bayesian Neural Networks (QBNNs) represent a novel approach to neural network architecture, integrating quantum superposition and entanglement to enhance ensemble learning performance, particularly when dealing with high-dimensional data. This paper explores the potential of QBNNs to overcome the limitations of classical ensembles by leveraging quantum phenomena for improved representation, processing, and generalization. We detail the design of a QBNN framework, focusing on the interplay between quantum states, Bayesian inference, and ensemble aggregation. The core claim centers on the design of a QBNN that utilizes quantum superposition and entanglement to achieve significantly enhanced accuracy and robustness in ensemble learning scenarios. The paper presents a comprehensive analysis of the theoretical and practical implications of this approach, including mathematical formulations and experimental validation demonstrating improvements over traditional ensemble methods. We discuss the challenges and future directions for this research, emphasizing the potential for transformative advancements in data analysis and machine learning.

•Sep 3, 2026•0 citations

A quantum algorithm for training wide and deep classical neural networks

Alexander Zlokapa, Hartmut Neven, Seth Lloyd

Given the success of deep learning in classical machine learning, quantum algorithms for traditional neural network architectures may provide one of the most promising settings for quantum machine learning. Considering a fully-connected feedforward neural network, we show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We propose a quantum algorithm to approximately train a wide and deep neural network up to $O(1/n)$ error for a training set of size $n$ by performing sparse matrix inversion in $O(\log n)$ time. To achieve an end-to-end exponential speedup over gradient descent, the data distribution must permit efficient state preparation and readout. We numerically demonstrate that the MNIST image dataset satisfies such conditions; moreover, the quantum algorithm matches the accuracy of the fully-connected network. Beyond the proven architecture, we provide empirical evidence for $O(\log n)$ training of a convolutional neural network with pooling.

arXiv:2107.09200•Jul 19, 2021•10 citations
Quantum machine learning promises great speedups over classical algorithms, but it often requires repeated computations to achieve a desired level of accuracy for its point estimates. Bayesian learning focuses more on sampling from posterior distributions than on point estimation, thus it might be more forgiving in the face of additional quantum noise. We propose a quantum algorithm for Bayesian neural network inference, drawing on recent advances in quantum deep learning, and simulate its empirical performance on several tasks. We find that already for small numbers of qubits, our algorithm approximates the true posterior well, while it does not require any repeated computations and thus fully realizes the quantum speedups.
The astounding acceleration in Artificial Intelligence and Quantum Computing advances naturally gives rise to a line of research, which unrolls the potential advantages of quantum computing on classical Machine Learning tasks, known as Quantum Machine Learning or Quantum Machine Intelligence. The typical objectives are either (1) exploring the potential quantum advantages on classical learning tasks or (2) levering well-established classical ML algorithms to tackle quantum-related problems on Noisy Intermediate-Scale Quantum (NISQ) devices. Along the second research direction, we study Quantum Neural Networks (QNNs) to accomplish the purpose of Bayesian learning. By observing a wide range of studies on QNNs, in which the sole training method is based on frequentist training, we find that Bayesian learning benefits QNNs from two aspects. First, Bayesian-trained models enjoy a high level of generalization due to the prior and posterior distribution usage compared to frequentist training, which will be justified by this paper’s theoretical study of model capacity. Second, Bayesian Inference offers epistemic uncertainty estimation, which merits the decision-making process. It is worth mentioning that frequentist-trained QNNs generally lack this desirable property. Under the Bayesian training procedure, our derived models can be considered a new class of QNNs (called BayesianQNNs) which possesses both desirable properties of Bayesian Inference while maintaining comparable predictive performance as frequentist counterparts. The proposed Bayesian Quantum Neural Networks is justified by empirical evidence from numerical experiments.
Quantum Bayesian Inference (QBI) presents a novel approach to statistical machine learning, utilizing the principles of quantum mechanics to enhance the accuracy and robustness of models, particularly when dealing with high-dimensional data and complex Bayesian frameworks. This paper introduces a quantum algorithm designed to efficiently estimate the posterior distribution of parameters in a Bayesian model through the application of quantum superposition and entanglement, aiming to overcome the limitations of classical methods. We explore the potential of this paradigm shift to deliver exponential speedups in inference tasks, offering a compelling path towards more accurate and reliable statistical machine learning algorithms.
Bayesian learning is ubiquitous for implementing classification and regression tasks, however, it is accompanied by computationally intractable limitations when the feature spaces become extremely large. Aiming to solve this problem, we develop a quantum bayesian learning framework of the restricted Boltzmann machine in the quantum-enhanced feature spaces. Our framework provides the encoding phase to map the real data and Boltzmann weight onto the quantum feature spaces and the training phase to learn an optimal inference function. Specifically, the training phase provides a physical quantity to measure the posterior distribution in quantum feature spaces, and this measure is utilized to design the quantum maximum a posterior (QMAP) algorithm and the quantum predictive distribution estimator (QPDE). It is shown that both quantum algorithms achieve exponential speed-up over their classical counterparts. Furthermore, it is interesting to note that our framework can figure out the classical bayesian learning tasks, i.e. processing the classical data and outputting corresponding classical labels. And a simulation, which is performed on an open-source software framework for quantum computing, illustrates that our algorithms show almost the same classification performance compared to their classical counterparts. Noting that the proposed quantum algorithms utilize the shallow circuit, our work is expected to be implemented on the noisy intermediate-scale quantum (NISQ) devices, and is one of the promising candidates to achieve quantum supremacy.
Quantum-enhanced Bayesian inference offers a paradigm shift in the field of machine learning, addressing the fundamental limitations of classical Bayesian methods – namely, computational complexity and scalability – when dealing with high-dimensional data. This paper presents a novel quantum-enhanced Bayesian inference algorithm designed to drastically reduce these challenges. We explore the use of quantum annealing and quantum approximate optimization algorithms to efficiently navigate the complex search space of model parameters, leading to significantly improved accuracy and reduced computational costs. This work demonstrates the potential of quantum computing to revolutionize machine learning, particularly within domains characterized by high data complexity and demanding performance requirements. The core mechanism focuses on leveraging quantum phenomena – superposition and entanglement – to accelerate the exploration of parameter space and improve the convergence of inference algorithms. The investigation includes a detailed analysis of the algorithm's performance compared to classical methods, highlighting the benefits of quantum acceleration in specific machine learning tasks.
Quantum Bayesian Neural Networks (QBNNs) represent a novel approach to neural network architecture, integrating quantum superposition and entanglement to enhance ensemble learning performance, particularly when dealing with high-dimensional data. This paper explores the potential of QBNNs to overcome the limitations of classical ensembles by leveraging quantum phenomena for improved representation, processing, and generalization. We detail the design of a QBNN framework, focusing on the interplay between quantum states, Bayesian inference, and ensemble aggregation. The core claim centers on the design of a QBNN that utilizes quantum superposition and entanglement to achieve significantly enhanced accuracy and robustness in ensemble learning scenarios. The paper presents a comprehensive analysis of the theoretical and practical implications of this approach, including mathematical formulations and experimental validation demonstrating improvements over traditional ensemble methods. We discuss the challenges and future directions for this research, emphasizing the potential for transformative advancements in data analysis and machine learning.
Given the success of deep learning in classical machine learning, quantum algorithms for traditional neural network architectures may provide one of the most promising settings for quantum machine learning. Considering a fully-connected feedforward neural network, we show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We propose a quantum algorithm to approximately train a wide and deep neural network up to O(1/n)O(1/n)O(1/n) error for a training set of size nnn by performing sparse matrix inversion in O(log⁡n)O(\log n)O(logn) time. To achieve an end-to-end exponential speedup over gradient descent, the data distribution must permit efficient state preparation and readout. We numerically demonstrate that the MNIST image dataset satisfies such conditions; moreover, the quantum algorithm matches the accuracy of the fully-connected network. Beyond the proven architecture, we provide empirical evidence for O(log⁡n)O(\log n)O(logn) training of a convolutional neural network with pooling.