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

Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics

Quantum Contextual Bandits: Integrating Bandit Exploration into Quantum Neural Network

Tianyi Chen, Shiva Raj Pokhrel, Jiang Fang, Yinlong Liu, Jiyan Sun, Liru Geng, Gang Li

Published Oct 5, 2025• 0 citations
Publisher

Abstract

Supervised quantum learning methods face notable limitations in dynamic, real-world environments due to their reliance on static labels and limited adaptability. To address these challenges, we propose a novel online learning framework — Quantum Contextual Bandit (QCB) — that integrates quantum neural networks (QNNs) with contextual bandit (CB) algorithms. The QCB framework enables adaptive decision-making by incorporating bandit-based exploration into QNN training, making it particularly suitable for applications such as recommender systems. To mitigate the adverse effects of quantum noise—including depolarizing, Pauli, and shot noise, the framework leverages a gradient-free optimization approach, enhancing robustness and convergence stability. Experimental results on various datasets demonstrate that QCB consistently outperforms traditional QNN training methods with identical circuit architectures. Notably, the model achieves over 99% accuracy under ideal conditions and sustains high performance under noisy quantum environments. These results underscore the potential of QCB as a scalable, noise-resilient solution for adaptive learning in quantum machine learning systems.

DOI
10.1109/smc58881.2025.11342551

Related papers

Quantum-Enhanced Neural Contextual Bandit Algorithms

Yuqi Huang, Vincent Y. F Tan, Sharu Theresa Jose

Stochastic contextual bandits are fundamental for sequential decision-making but pose significant challenges for existing neural network-based algorithms, particularly when scaling to quantum neural networks (QNNs) due to issues such as massive over-parameterization, computational instability, and the barren plateau phenomenon. This paper introduces the Quantum Neural Tangent Kernel-Upper Confidence Bound (QNTK-UCB) algorithm, a novel algorithm that leverages the Quantum Neural Tangent Kernel (QNTK) to address these limitations. By freezing the QNN at a random initialization and utilizing its static QNTK as a kernel for ridge regression, QNTK-UCB bypasses the unstable training dynamics inherent in explicit parameterized quantum circuit training while fully exploiting the unique quantum inductive bias. For a time horizon $T$ and $K$ actions, our theoretical analysis reveals a significantly improved parameter scaling of $Ω((TK)^3)$ for QNTK-UCB, a substantial reduction compared to $Ω((TK)^8)$ required by classical NeuralUCB algorithms for similar regret guarantees. Empirical evaluations on non-linear synthetic benchmarks and quantum-native variational quantum eigensolver tasks demonstrate QNTK-UCB's superior sample efficiency in low-data regimes. This work highlights how the inherent properties of QNTK provide implicit regularization and a sharper spectral decay, paving the way for achieving ``quantum advantage'' in online learning.

cs.LGCross-listedarXiv:2601.02870•Jan 7, 2026•1 citation

Quantum Neural Network Adjustment

Jincheng Zhang

Quantum Neural Networks (QNNs) represent a promising paradigm in artificial intelligence, leveraging the unique properties of quantum mechanics to potentially surpass classical neural networks. This paper investigates a novel approach to QNNs – Adaptive Quantum Neural Network Adjustment – designed to dynamically optimize network parameters, thereby enhancing performance across a range of applications. We propose a mechanism that iteratively adjusts the network's weights based on feedback from a quantum-enhanced learning process, fostering a more robust and adaptable system. The paper details the architecture of the adaptive adjustment mechanism, explores its impact on network performance through simulations, and provides a preliminary analysis of its potential benefits. The core of the work centers around a novel quantum-inspired optimization strategy to address the limitations of traditional training methods. This research highlights the potential of incorporating adaptive adjustment into QNN architectures to achieve superior results.

•Aug 31, 2026•0 citations

Quantum Machine Learning Adaptive Optimizer

Jincheng Zhang

Quantum Machine Learning (QML) presents a paradigm shift in computational paradigms, offering the potential for breakthroughs in various fields, including machine learning. This paper explores the application of Quantum Neural Networks (QNNs) to a novel adaptive optimization framework, termed "Quantum Adaptive Optimizer" (QAO). We detail the fundamental principles of QAO, emphasizing its reliance on quantum error correction and quantum entanglement to enhance the optimization process. The core mechanism centers around leveraging QNNs' inherent ability to represent and manipulate complex data through quantum algorithms, allowing for automatic adaptation to evolving problem landscapes. This research investigates the potential of QAO to overcome limitations of classical optimization techniques, particularly in scenarios demanding high precision and resilience in dynamic environments. The paper concludes with a discussion of the challenges and future directions of this innovative approach.

•Sep 6, 2026•0 citations

Enhancing Gradient Variance and Differential Privacy in Quantum Federated Learning

Phan Duc Thien, Minh-Duong Nguyen, Quoc‐Viet Pham +1 more

Upon integrating Quantum Neural Network (QNN) as the local model, Quantum Federated Learning (QFL) has recently confronted notable challenges. Firstly, exploration is hindered over sharp minima, decreasing learning performance. Secondly, the steady gradient descent results in more stable and predictable model transmissions over wireless channels, making the model more susceptible to attacks from adversarial entities. Additionally, the local QFL model is vulnerable to noise produced by the quantum device's intermediate noise states, since it requires the use of quantum gates and circuits for training. This local noise becomes intertwined with learning parameters during training, impairing model precision and convergence rate. To address these issues, we propose a new QFL technique that incorporates differential privacy and introduces a dedicated noise estimation strategy to quantify and mitigate the impact of intermediate quantum noise. Furthermore, we design an adaptive noise generation scheme to alleviate privacy threats associated with the vanishing gradient variance phenomenon of QNN and enhance robustness against device noise. Experimental results demonstrate that our algorithm effectively balances convergence, reduces communication costs, and mitigates the adverse effects of intermediate quantum noise while maintaining strong privacy protection. Using real-world datasets, we achieved test accuracy of up to 98.47% for the MNIST dataset and 83.85% for the CIFAR-10 dataset while maintaining fast execution times.

arXiv:2509.05377•Sep 11, 2025•1 citation

Q Learning with Quantum Neural Networks

Wei Hu, James Lee Hu

Applying quantum computing techniques to machine learning has attracted widespread attention recently and quantum machine learning has become a hot research topic. There are three major categories of machine learning: supervised, unsupervised, and reinforcement learning (RL). However, quantum RL has made the least progress when compared to the other two areas. In this study, we implement the well-known RL algorithm Q learning with a quantum neural network and evaluate it in the grid world environment. RL is learning through interactions with the environment, with the aim of discovering a strategy to maximize the expected cumulative rewards. Problems in RL bring in unique challenges to the study with their sequential nature of learning, potentially long delayed reward signals, and large or infinite size of state and action spaces. This study extends our previous work on solving the contextual bandit problem using a quantum neural network, where the reward signals are immediate after each action.

Natural Science•Jan 1, 2019•6 citations

Equivariant Split Attention Quantum Neural Networks for Intelligent Stock Market Prediction Systems

Nozomi Leroux-Martin

The rapid advancement of artificial intelligence, deep learning, and quantum computing has significantly transformed stock market prediction and financial analytics. Traditional statistical models are limited in capturing the nonlinear, stochastic, and high-dimensional nature of financial time series, leading to the adoption of advanced hybrid computational frameworks. This review presents an optimized equivariant split attention quantum neural network (OESAQNN) framework for stock market prediction and recommendation systems. The architecture integrates quantum neural networks with equivariant learning to preserve structural relationships in financial data, while split attention mechanisms enhance feature extraction by focusing on relevant temporal and contextual patterns. The study explores hybrid classical-quantum optimization techniques, including parameter-shift gradient methods and adaptive optimization algorithms, to improve convergence and computational efficiency. It also incorporates multimodal datasets such as historical prices, sentiment data, and macroeconomic indicators for robust prediction. Results demonstrate improved accuracy, scalability, and interpretability compared to conventional deep learning models.Overall, the proposed framework offers a promising direction for developing intelligent, efficient, and next-generation financial forecasting and recommendation systems for real-time decision-making.

International Journal on Advanced Electrical and Computer Engineering•Mar 1, 2023•0 citations
Supervised quantum learning methods face notable limitations in dynamic, real-world environments due to their reliance on static labels and limited adaptability. To address these challenges, we propose a novel online learning framework — Quantum Contextual Bandit (QCB) — that integrates quantum neural networks (QNNs) with contextual bandit (CB) algorithms. The QCB framework enables adaptive decision-making by incorporating bandit-based exploration into QNN training, making it particularly suitable for applications such as recommender systems. To mitigate the adverse effects of quantum noise—including depolarizing, Pauli, and shot noise, the framework leverages a gradient-free optimization approach, enhancing robustness and convergence stability. Experimental results on various datasets demonstrate that QCB consistently outperforms traditional QNN training methods with identical circuit architectures. Notably, the model achieves over 99% accuracy under ideal conditions and sustains high performance under noisy quantum environments. These results underscore the potential of QCB as a scalable, noise-resilient solution for adaptive learning in quantum machine learning systems.
Stochastic contextual bandits are fundamental for sequential decision-making but pose significant challenges for existing neural network-based algorithms, particularly when scaling to quantum neural networks (QNNs) due to issues such as massive over-parameterization, computational instability, and the barren plateau phenomenon. This paper introduces the Quantum Neural Tangent Kernel-Upper Confidence Bound (QNTK-UCB) algorithm, a novel algorithm that leverages the Quantum Neural Tangent Kernel (QNTK) to address these limitations. By freezing the QNN at a random initialization and utilizing its static QNTK as a kernel for ridge regression, QNTK-UCB bypasses the unstable training dynamics inherent in explicit parameterized quantum circuit training while fully exploiting the unique quantum inductive bias. For a time horizon TTT and KKK actions, our theoretical analysis reveals a significantly improved parameter scaling of Ω((TK)3)Ω((TK)^3)Ω((TK)3) for QNTK-UCB, a substantial reduction compared to Ω((TK)8)Ω((TK)^8)Ω((TK)8) required by classical NeuralUCB algorithms for similar regret guarantees. Empirical evaluations on non-linear synthetic benchmarks and quantum-native variational quantum eigensolver tasks demonstrate QNTK-UCB's superior sample efficiency in low-data regimes. This work highlights how the inherent properties of QNTK provide implicit regularization and a sharper spectral decay, paving the way for achieving ``quantum advantage'' in online learning.
Quantum Neural Networks (QNNs) represent a promising paradigm in artificial intelligence, leveraging the unique properties of quantum mechanics to potentially surpass classical neural networks. This paper investigates a novel approach to QNNs – Adaptive Quantum Neural Network Adjustment – designed to dynamically optimize network parameters, thereby enhancing performance across a range of applications. We propose a mechanism that iteratively adjusts the network's weights based on feedback from a quantum-enhanced learning process, fostering a more robust and adaptable system. The paper details the architecture of the adaptive adjustment mechanism, explores its impact on network performance through simulations, and provides a preliminary analysis of its potential benefits. The core of the work centers around a novel quantum-inspired optimization strategy to address the limitations of traditional training methods. This research highlights the potential of incorporating adaptive adjustment into QNN architectures to achieve superior results.
Quantum Machine Learning (QML) presents a paradigm shift in computational paradigms, offering the potential for breakthroughs in various fields, including machine learning. This paper explores the application of Quantum Neural Networks (QNNs) to a novel adaptive optimization framework, termed "Quantum Adaptive Optimizer" (QAO). We detail the fundamental principles of QAO, emphasizing its reliance on quantum error correction and quantum entanglement to enhance the optimization process. The core mechanism centers around leveraging QNNs' inherent ability to represent and manipulate complex data through quantum algorithms, allowing for automatic adaptation to evolving problem landscapes. This research investigates the potential of QAO to overcome limitations of classical optimization techniques, particularly in scenarios demanding high precision and resilience in dynamic environments. The paper concludes with a discussion of the challenges and future directions of this innovative approach.
Upon integrating Quantum Neural Network (QNN) as the local model, Quantum Federated Learning (QFL) has recently confronted notable challenges. Firstly, exploration is hindered over sharp minima, decreasing learning performance. Secondly, the steady gradient descent results in more stable and predictable model transmissions over wireless channels, making the model more susceptible to attacks from adversarial entities. Additionally, the local QFL model is vulnerable to noise produced by the quantum device's intermediate noise states, since it requires the use of quantum gates and circuits for training. This local noise becomes intertwined with learning parameters during training, impairing model precision and convergence rate. To address these issues, we propose a new QFL technique that incorporates differential privacy and introduces a dedicated noise estimation strategy to quantify and mitigate the impact of intermediate quantum noise. Furthermore, we design an adaptive noise generation scheme to alleviate privacy threats associated with the vanishing gradient variance phenomenon of QNN and enhance robustness against device noise. Experimental results demonstrate that our algorithm effectively balances convergence, reduces communication costs, and mitigates the adverse effects of intermediate quantum noise while maintaining strong privacy protection. Using real-world datasets, we achieved test accuracy of up to 98.47% for the MNIST dataset and 83.85% for the CIFAR-10 dataset while maintaining fast execution times.
Applying quantum computing techniques to machine learning has attracted widespread attention recently and quantum machine learning has become a hot research topic. There are three major categories of machine learning: supervised, unsupervised, and reinforcement learning (RL). However, quantum RL has made the least progress when compared to the other two areas. In this study, we implement the well-known RL algorithm Q learning with a quantum neural network and evaluate it in the grid world environment. RL is learning through interactions with the environment, with the aim of discovering a strategy to maximize the expected cumulative rewards. Problems in RL bring in unique challenges to the study with their sequential nature of learning, potentially long delayed reward signals, and large or infinite size of state and action spaces. This study extends our previous work on solving the contextual bandit problem using a quantum neural network, where the reward signals are immediate after each action.
The rapid advancement of artificial intelligence, deep learning, and quantum computing has significantly transformed stock market prediction and financial analytics. Traditional statistical models are limited in capturing the nonlinear, stochastic, and high-dimensional nature of financial time series, leading to the adoption of advanced hybrid computational frameworks. This review presents an optimized equivariant split attention quantum neural network (OESAQNN) framework for stock market prediction and recommendation systems. The architecture integrates quantum neural networks with equivariant learning to preserve structural relationships in financial data, while split attention mechanisms enhance feature extraction by focusing on relevant temporal and contextual patterns. The study explores hybrid classical-quantum optimization techniques, including parameter-shift gradient methods and adaptive optimization algorithms, to improve convergence and computational efficiency. It also incorporates multimodal datasets such as historical prices, sentiment data, and macroeconomic indicators for robust prediction. Results demonstrate improved accuracy, scalability, and interpretability compared to conventional deep learning models.Overall, the proposed framework offers a promising direction for developing intelligent, efficient, and next-generation financial forecasting and recommendation systems for real-time decision-making.