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:2206.04734 · neural information processing systems

Fast Bayesian Inference with Batch Bayesian Quadrature Via Kernel Recombination

Masaki Adachi, Satoshi Hayakawa, Martin Jørgensen, Harald Oberhauser, Michael A Osborne

Published Jan 1, 2022• 4 citations
arXivHTMLPDF

Abstract

Calculation of Bayesian posteriors and model evidences typically requires numerical integration. Bayesian quadrature (BQ), a surrogate-model-based approach to numerical integration, is capable of superb sample efficiency, but its lack of parallelisation has hindered its practical applications. In this work, we propose a parallelised (batch) BQ method, employing techniques from kernel quadrature, that possesses an empirically exponential convergence rate. Additionally, just as with Nested Sampling, our method permits simultaneous inference of both posteriors and model evidence. Samples from our BQ surrogate model are re-selected to give a sparse set of samples, via a kernel recombination algorithm, requiring negligible additional time to increase the batch size. Empirically, we find that our approach significantly outperforms the sampling efficiency of both state-of-the-art BQ techniques and Nested Sampling in various real-world datasets, including lithium-ion battery analytics.

DOI
10.52202/068431-1203

Related papers

Quantum-Inspired Bayesian Inference for High-Dimensional Regression

Jincheng Zhang

High-dimensional regression problems, prevalent in diverse fields like genomics, finance, and medical diagnostics, pose a significant challenge to classical Bayesian inference. The computational cost of calculating posterior distributions often scales exponentially with the number of parameters, rendering many real-world applications intractable. This paper introduces a novel Bayesian inference algorithm inspired by the principles of quantum mechanics, specifically superposition and interference. We represent the prior distribution as a superposition of states, allowing for simultaneous exploration of the entire parameter space. Inference is then performed through a "quantum-inspired" sampling process that mimics the probabilistic nature of quantum measurements. This approach offers a potential pathway to circumvent the computational bottlenecks inherent in traditional Bayesian methods, particularly in the context of high-dimensional data. We outline the key components of the algorithm, provide a theoretical framework, and discuss its potential advantages and limitations. The core of the method lies in effectively harnessing the parallel exploration capability suggested by quantum mechanics to drastically reduce the computational burden associated with estimating the posterior distribution.

•Aug 28, 2026•0 citations

Quantum inference on Bayesian networks

Guang Hao Low, Theodore J. Yoder, Isaac L. Chuang

Performing exact inference on Bayesian networks is known to be $#P$-hard. Typically approximate inference techniques are used instead to sample from the distribution on query variables given the values $e$ of evidence variables. Classically, a single unbiased sample is obtained from a Bayesian network on $n$ variables with at most $m$ parents per node in time $O(nmP{(e)}^{\ensuremath{-}1})$, depending critically on $P(e)$, the probability that the evidence might occur in the first place. By implementing a quantum version of rejection sampling, we obtain a square-root speedup, taking $O(n{2}^{m}P{(e)}^{\ensuremath{-}\frac{1}{2}})$ time per sample. We exploit the Bayesian network's graph structure to efficiently construct a quantum state, a q-sample, representing the intended classical distribution, and also to efficiently apply amplitude amplification, the source of our speedup. Thus, our speedup is notable as it is unrelativized---we count primitive operations and require no blackbox oracle queries.

arXiv:1402.7359•Physical Review A•Jun 13, 2014•109 citations

Quantum Bayesian Neural Networks

Noah Berner, Vincent Fortuin, Jonas Landman

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.

arXiv:2107.09599•Jul 20, 2021•5 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 Inference based on Quantum Computing

Jincheng Zhang

This paper explores the application of quantum computing to accelerate Bayesian inference. Traditional Bayesian inference suffers from significant computational bottlenecks, particularly in complex models with large datasets. We propose a novel approach leveraging the inherent parallelism of quantum computers to drastically reduce the time required for inference. Specifically, we design a quantum algorithm based on a parameterized quantum circuit (PQC) to perform Bayesian updating. This approach utilizes quantum superposition and interference to perform computations on multiple possibilities simultaneously. The core claim is that this method can significantly speed up Bayesian inference. We detail the mathematical formulation of the algorithm, including the quantum circuit representation and the key operations involved. The potential of this approach to overcome the limitations of classical Bayesian inference is discussed, highlighting the transformative impact of quantum computing on probabilistic reasoning and data analysis. The efficiency gains are expected to be particularly pronounced for problems where the prior distributions and the likelihood functions are highly correlated, allowing for efficient quantum interference.

•Sep 3, 2026•0 citations

Title: Adaptive Quantum Sampling for Bayesian Inference

Jincheng Zhang

This paper introduces an adaptive quantum sampling method designed to enhance the efficiency of Bayesian inference in complex, high-dimensional spaces. Traditional Bayesian inference methods often struggle with the computational complexity of exploring the vast parameter space, leading to slow convergence and limited accuracy. We propose a novel quantum sampling algorithm that dynamically adjusts the sampling process based on uncertainty estimates generated by quantum computations. This adaptive approach mitigates the inherent challenges of sampling in high-dimensional spaces, resulting in significantly faster convergence and improved inference accuracy. The core mechanism leverages quantum algorithms to identify promising regions of the parameter space, thereby reducing the computational burden and enhancing the effectiveness of Bayesian modeling. The paper details the theoretical framework underpinning the algorithm, outlines the implementation of the quantum sampling process, and provides a comprehensive analysis of its performance compared to traditional sampling techniques. Finally, we present preliminary experimental results demonstrating the effectiveness of the proposed method across a range of complex scenarios.

•Aug 29, 2026•0 citations
Calculation of Bayesian posteriors and model evidences typically requires numerical integration. Bayesian quadrature (BQ), a surrogate-model-based approach to numerical integration, is capable of superb sample efficiency, but its lack of parallelisation has hindered its practical applications. In this work, we propose a parallelised (batch) BQ method, employing techniques from kernel quadrature, that possesses an empirically exponential convergence rate. Additionally, just as with Nested Sampling, our method permits simultaneous inference of both posteriors and model evidence. Samples from our BQ surrogate model are re-selected to give a sparse set of samples, via a kernel recombination algorithm, requiring negligible additional time to increase the batch size. Empirically, we find that our approach significantly outperforms the sampling efficiency of both state-of-the-art BQ techniques and Nested Sampling in various real-world datasets, including lithium-ion battery analytics.
High-dimensional regression problems, prevalent in diverse fields like genomics, finance, and medical diagnostics, pose a significant challenge to classical Bayesian inference. The computational cost of calculating posterior distributions often scales exponentially with the number of parameters, rendering many real-world applications intractable. This paper introduces a novel Bayesian inference algorithm inspired by the principles of quantum mechanics, specifically superposition and interference. We represent the prior distribution as a superposition of states, allowing for simultaneous exploration of the entire parameter space. Inference is then performed through a "quantum-inspired" sampling process that mimics the probabilistic nature of quantum measurements. This approach offers a potential pathway to circumvent the computational bottlenecks inherent in traditional Bayesian methods, particularly in the context of high-dimensional data. We outline the key components of the algorithm, provide a theoretical framework, and discuss its potential advantages and limitations. The core of the method lies in effectively harnessing the parallel exploration capability suggested by quantum mechanics to drastically reduce the computational burden associated with estimating the posterior distribution.
Performing exact inference on Bayesian networks is known to be $#P$-hard. Typically approximate inference techniques are used instead to sample from the distribution on query variables given the values eee of evidence variables. Classically, a single unbiased sample is obtained from a Bayesian network on nnn variables with at most mmm parents per node in time $O(nmP{(e)}^{\ensuremath{-}1})$, depending critically on P(e)P(e)P(e), the probability that the evidence might occur in the first place. By implementing a quantum version of rejection sampling, we obtain a square-root speedup, taking $O(n{2}^{m}P{(e)}^{\ensuremath{-}\frac{1}{2}})$ time per sample. We exploit the Bayesian network's graph structure to efficiently construct a quantum state, a q-sample, representing the intended classical distribution, and also to efficiently apply amplitude amplification, the source of our speedup. Thus, our speedup is notable as it is unrelativized---we count primitive operations and require no blackbox oracle queries.
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.
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.
This paper explores the application of quantum computing to accelerate Bayesian inference. Traditional Bayesian inference suffers from significant computational bottlenecks, particularly in complex models with large datasets. We propose a novel approach leveraging the inherent parallelism of quantum computers to drastically reduce the time required for inference. Specifically, we design a quantum algorithm based on a parameterized quantum circuit (PQC) to perform Bayesian updating. This approach utilizes quantum superposition and interference to perform computations on multiple possibilities simultaneously. The core claim is that this method can significantly speed up Bayesian inference. We detail the mathematical formulation of the algorithm, including the quantum circuit representation and the key operations involved. The potential of this approach to overcome the limitations of classical Bayesian inference is discussed, highlighting the transformative impact of quantum computing on probabilistic reasoning and data analysis. The efficiency gains are expected to be particularly pronounced for problems where the prior distributions and the likelihood functions are highly correlated, allowing for efficient quantum interference.
This paper introduces an adaptive quantum sampling method designed to enhance the efficiency of Bayesian inference in complex, high-dimensional spaces. Traditional Bayesian inference methods often struggle with the computational complexity of exploring the vast parameter space, leading to slow convergence and limited accuracy. We propose a novel quantum sampling algorithm that dynamically adjusts the sampling process based on uncertainty estimates generated by quantum computations. This adaptive approach mitigates the inherent challenges of sampling in high-dimensional spaces, resulting in significantly faster convergence and improved inference accuracy. The core mechanism leverages quantum algorithms to identify promising regions of the parameter space, thereby reducing the computational burden and enhancing the effectiveness of Bayesian modeling. The paper details the theoretical framework underpinning the algorithm, outlines the implementation of the quantum sampling process, and provides a comprehensive analysis of its performance compared to traditional sampling techniques. Finally, we present preliminary experimental results demonstrating the effectiveness of the proposed method across a range of complex scenarios.