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:2501.02005 · Journal of the Korean Physical Society

Machine learns quantum complexity

Dongsu Bak A, Su-Hyeong Kim, Sangnam Park, Jeong-Pil Song

Published Nov 21, 2025• 0 citations
arXivHTMLPDF
DOI
10.1007/s40042-025-01529-w

Related papers

Machine Learning and Quantum

Pengfei Zhang

Bulletin of the American Physical Society•Mar 6, 2020•0 citations

Quantum Machine Learning Adaptive Complexity Adjustment

Jincheng Zhang

This paper presents a novel quantum machine learning algorithm, Quantum Machine Learning Adaptive Complexity Adjustment (QML-MAC), designed to automatically adjust the complexity of a learning process based on the characteristics of the input data. Traditional machine learning algorithms frequently employ fixed parameters, which can limit the algorithm's effectiveness. QML-MAC leverages quantum mechanics principles to dynamically modify the complexity of the learning process, thereby improving learning efficiency and potentially unlocking new capabilities. This research explores the potential of quantum algorithms to enhance optimization and data handling, specifically focusing on adapting to the inherent complexities within datasets. The core mechanism centers around a quantum-enhanced learning loop that iteratively adjusts the complexity, leading to improved performance and reduced computational resources.

•Aug 31, 2026•0 citations

Quantum machine learning

Ivan B. Djordjević

Elsevier eBooks•Jul 22, 2022•0 citations

Complexity Theory Quantum Machine Learning Algorithm Design

Jincheng Zhang

This paper explores the application of complexity theory to the design of quantum machine learning algorithms. The core claim is to develop a quantum machine learning algorithm that leverages the principles of complexity theory to optimize model parameters and training processes, ultimately enhancing model generalization capabilities. Traditional machine learning often focuses on data features, but this research proposes a novel approach that utilizes complexity theory to dynamically restructure model parameters and training pathways. The paper details the theoretical underpinnings of complexity theory, its application to algorithm design, and the potential benefits of this methodology. We present a preliminary implementation demonstrating a potential improvement in performance compared to existing quantum machine learning approaches.

•Sep 3, 2026•0 citations

Quantum Machine Learning

Osama M. Raisuddin, Suvranu De

Springer eBooks•Nov 14, 2025•0 citations

Quantum circuit complexity and unsupervised machine learning of topological order

Yanming Che, Clemens Gneiting, Xiaoguang Wang +1 more

Enabling the discovery of unknown quantum many-body phases of matter remains a fundamental challenge in machine learning for quantum physics. Here, inspired by the close relationship between Kolmogorov complexity and unsupervised machine learning, we explore quantum circuit complexity as a pivot to build intuitive and efficient unsupervised machine learning for topological order in quantum many-body systems. We argue that Nielsen's quantum circuit complexity serves as an intrinsic informational distance between topological quantum states that results in interpretable manifold learning. To span a bridge from conceptual power to practical applicability, we present two theorems that connect Nielsen's quantum circuit complexity of quantum path planning with quantum Fisher complexity (Bures distance) and entanglement generation, respectively. The resulting kernel functions demonstrate superior performance and enhanced interpretability in numerical multiqubit experiments. Our results establish connections between key concepts of quantum computation, quantum complexity, quantum metrology, and machine learning of topological quantum order.

arXiv:2508.04486•Nature Communications•Apr 8, 2026•3 citations
This paper presents a novel quantum machine learning algorithm, Quantum Machine Learning Adaptive Complexity Adjustment (QML-MAC), designed to automatically adjust the complexity of a learning process based on the characteristics of the input data. Traditional machine learning algorithms frequently employ fixed parameters, which can limit the algorithm's effectiveness. QML-MAC leverages quantum mechanics principles to dynamically modify the complexity of the learning process, thereby improving learning efficiency and potentially unlocking new capabilities. This research explores the potential of quantum algorithms to enhance optimization and data handling, specifically focusing on adapting to the inherent complexities within datasets. The core mechanism centers around a quantum-enhanced learning loop that iteratively adjusts the complexity, leading to improved performance and reduced computational resources.
This paper explores the application of complexity theory to the design of quantum machine learning algorithms. The core claim is to develop a quantum machine learning algorithm that leverages the principles of complexity theory to optimize model parameters and training processes, ultimately enhancing model generalization capabilities. Traditional machine learning often focuses on data features, but this research proposes a novel approach that utilizes complexity theory to dynamically restructure model parameters and training pathways. The paper details the theoretical underpinnings of complexity theory, its application to algorithm design, and the potential benefits of this methodology. We present a preliminary implementation demonstrating a potential improvement in performance compared to existing quantum machine learning approaches.
Enabling the discovery of unknown quantum many-body phases of matter remains a fundamental challenge in machine learning for quantum physics. Here, inspired by the close relationship between Kolmogorov complexity and unsupervised machine learning, we explore quantum circuit complexity as a pivot to build intuitive and efficient unsupervised machine learning for topological order in quantum many-body systems. We argue that Nielsen's quantum circuit complexity serves as an intrinsic informational distance between topological quantum states that results in interpretable manifold learning. To span a bridge from conceptual power to practical applicability, we present two theorems that connect Nielsen's quantum circuit complexity of quantum path planning with quantum Fisher complexity (Bures distance) and entanglement generation, respectively. The resulting kernel functions demonstrate superior performance and enhanced interpretability in numerical multiqubit experiments. Our results establish connections between key concepts of quantum computation, quantum complexity, quantum metrology, and machine learning of topological quantum order.