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:2202.04238 · Physical Review Research

Parametric t-stochastic neighbor embedding with quantum neural network

Yoshiaki Kawase, Kosuke Mitarai, Keisuke Fujii

Published Dec 19, 2022• 17 citations
arXivHTMLPDF

Abstract

t-stochastic neighbor embedding (t-SNE) is a nonparametric data visualization method in classical machine learning. It maps the data from the high-dimensional space into a low-dimensional space, especially a two-dimensional plane, while maintaining the relationship or similarities between the surrounding points. In t-SNE, the initial position of the low-dimensional data is randomly determined, and the visualization is achieved by moving the low-dimensional data to minimize a cost function. Its variant called parametric t-SNE uses neural networks for this mapping. In this paper, we propose to use quantum neural networks for parametric t-SNE to reflect the characteristics of high-dimensional quantum data on low-dimensional data. We use fidelity-based metrics instead of Euclidean distance in calculating high-dimensional data similarity. To verify our proposed method, we visualize both classical (Iris dataset) and quantum (time-depending Hamiltonian dynamics) data for classification tasks. Since this method allows us to represent a quantum dataset in a higher dimensional Hilbert space by a quantum dataset in a lower dimension while keeping their similarity, the proposed method can also be used to compress quantum data for further quantum machine learning.

DOI
10.1103/physrevresearch.4.043199

Related papers

Quantum-enhanced t-stochastic neighbor embedding for high-dimensional data visualization

Xin Zhang, Chao‐Hua Yu, Gongde Guo +1 more

t-distributed stochastic neighbor embedding (t-SNE) is a nonlinear dimensionality reduction algorithm that preserves local similarity by matching probability distributions between high- and low-dimensional spaces. Owing to its ability to capture complex manifold structures, t-SNE has become a widely used technique for high-dimensional data visualization. However, it still faces significant computational challenges when dealing with large-scale datasets. In this paper, we present a quantum-enhanced t-SNE algorithm that achieves a quadratic speedup with respect to the number of data samples. Specifically, three unitary operators are constructed using quantum arithmetic and comparators to compute the probability distributions. By integrating them with the Hadamard transform, the gradients of the Kullback-Leibler divergence can be efficiently computed. Moreover, since a complete quantum procedure is provided, our method surpasses the performance of existing quantum variants.

Physical Review Research•Apr 6, 2026•0 citations

Non-Parametric Semi-Supervised Learning in Many-Body Hilbert Space with Rescaled Logarithmic Fidelity

Weiming Li, Shi-Ju Ran

In quantum and quantum-inspired machine learning, a key step is to embed the data in the quantum space known as Hilbert space. Studying quantum kernel function, which defines the distances among the samples in the Hilbert space, belongs to the fundamental topics in this direction. In this work, we propose a tunable quantum-inspired kernel function (QIKF) named rescaled logarithmic fidelity (RLF) and a non-parametric algorithm for the semi-supervised learning in the quantum space. The rescaling takes advantage of the non-linearity of the kernel to tune the mutual distances of samples in the Hilbert space, and meanwhile avoids the exponentially-small fidelities between quantum many-qubit states. Being non-parametric excludes the possible effects from the variational parameters, and evidently demonstrates the properties of the kernel itself. Our results on the hand-written digits (MNIST dataset) and movie reviews (IMDb dataset) support the validity of our method, by comparing with the standard fidelity as the QIKF as well as several well-known non-parametric algorithms (naive Bayes classifiers, k-nearest neighbors, and spectral clustering). High accuracy is demonstrated, particularly for the unsupervised case with no labeled samples and the few-shot cases with small numbers of labeled samples. With the visualizations by t-stochastic neighbor embedding, our results imply that the machine learning in the Hilbert space complies with the principles of maximal coding rate reduction, where the low-dimensional data exhibit within-class compressibility, between-class discrimination, and overall diversity. The proposed QIKF and semi-supervised algorithm can be further combined with the parametric models such as tensor networks, quantum circuits, and quantum neural networks.

arXiv:2107.00195•Mathematics•Mar 15, 2022•6 citations

Visual assessment of multi-photon interference

Fulvio Flamini, Nicolò Spagnolo, Fabio Sciarrino

Classical machine learning algorithms can provide insights on high-dimensional processes that are hardly accessible with conventional approaches. As a notable example, t -distributed Stochastic Neighbor Embedding ( t -SNE) represents the state of the art for visualization of data sets of large dimensionality. An interesting question is then if this algorithm can provide useful information also in quantum experiments with very large Hilbert spaces. Leveraging these considerations, in this work we apply t -SNE to probe the spatial distribution of n -photon events in m -dimensional Hilbert spaces, showing that its findings can be beneficial for validating genuine quantum interference in boson sampling experiments. In particular, we find that nonlinear dimensionality reduction is capable to capture distinctive features in the spatial distribution of data related to multi-photon states with different evolutions. We envisage that this approach will inspire further theoretical investigations, for instance for a reliable assessment of quantum computational advantage.

Quantum Science and Technology•Feb 7, 2019•19 citations

Variational Quantum Self-Organizing Map

Deshmukh, Amol

We propose a novel quantum neural network architecture for unsupervised learning of classical and quantum data based on the kernelized version of Kohonen's self-organizing map. The central idea behind our algorithm is to replace the Euclidean distance metric with the fidelity between quantum states to identify the best matching unit from the low-dimensional grid of output neurons in the self-organizing map. The fidelities between the unknown quantum state and the quantum states containing the variational parameters are estimated by computing the transition probability on a quantum computer. The estimated fidelities are in turn used to adjust the variational parameters of the output neurons. Unlike $\mathcal{O}(N^{2})$ circuit evaluations needed in quantum kernel estimation, our algorithm requires $\mathcal{O}(N)$ circuit evaluations for $N$ data samples. Analogous to the classical version of the self-organizing map, our algorithm learns a mapping from a high-dimensional Hilbert space to a low-dimensional grid of lattice points while preserving the underlying topology of the Hilbert space. We showcase the effectiveness of our algorithm by constructing a two-dimensional visualization that accurately differentiates between the three distinct species of flowers in Fisher's Iris dataset. In addition, we demonstrate the efficacy of our approach on quantum data by creating a two-dimensional map that preserves the topology of the state space in the Schwinger model and distinguishes between the two separate phases of the model at $θ= π$.

arXiv:2504.03584•Apr 4, 2025•1 citation

Non-parametric Active Learning and Rate Reduction in Many-body Hilbert Space with Rescaled Logarithmic Fidelity.

Weiming Li, Shi-Ju Ran

In quantum and quantum-inspired machine learning, the very first step is to embed the data in quantum space known as Hilbert space. Developing quantum kernel function (QKF), which defines the distances among the samples in the Hilbert space, belongs to the fundamental topics for machine learning. In this work, we propose the rescaled logarithmic fidelity (RLF) and a non-parametric active learning in the quantum space, which we name as RLF-NAL. The rescaling takes advantage of the non-linearity of the kernel to tune the mutual distances of samples in the Hilbert space, and meanwhile avoids the exponentially-small fidelities between quantum many-qubit states. We compare RLF-NAL with several well-known non-parametric algorithms including naive Bayes classifiers, $k$-nearest neighbors, and spectral clustering. Our method exhibits excellent accuracy particularly for the unsupervised case with no labeled samples and the few-shot cases with small numbers of labeled samples. With the visualizations by t-SNE, our results imply that the machine learning in the Hilbert space complies with the principles of maximal coding rate reduction, where the low-dimensional data exhibit within-class compressibility, between-class discrimination, and overall diversity. Our proposals can be applied to other quantum and quantum-inspired machine learning, including the methods using the parametric models such as tensor networks, quantum circuits, and quantum neural networks.

•Jul 1, 2021•0 citations

An Evaluation of Hardware-Efficient Quantum Neural Networks for Image Data Classification

Tuyen Nguyen, Incheon Paik, Yutaka Watanobe +1 more

Quantum computing is expected to fundamentally change computer systems in the future. Recently, a new research topic of quantum computing is the hybrid quantum–classical approach for machine learning, in which a parameterized quantum circuit, also called quantum neural network (QNN), is optimized by a classical computer. This hybrid approach can have the benefits of both quantum computing and classical machine learning methods. In this early stage, it is of crucial importance to understand the new characteristics of quantum neural networks for different machine learning tasks. In this paper, we will study quantum neural networks for the task of classifying images, which are high-dimensional spatial data. In contrast to previous evaluations of low-dimensional or scalar data, we will investigate the impacts of practical encoding types, circuit depth, bias term, and readout on classification performance on the popular MNIST image dataset. Various interesting findings on learning behaviors of different QNNs are obtained through experimental results. To the best of our knowledge, this is the first work that considers various QNN aspects for image data.

Electronics•Feb 1, 2022•34 citations
t-stochastic neighbor embedding (t-SNE) is a nonparametric data visualization method in classical machine learning. It maps the data from the high-dimensional space into a low-dimensional space, especially a two-dimensional plane, while maintaining the relationship or similarities between the surrounding points. In t-SNE, the initial position of the low-dimensional data is randomly determined, and the visualization is achieved by moving the low-dimensional data to minimize a cost function. Its variant called parametric t-SNE uses neural networks for this mapping. In this paper, we propose to use quantum neural networks for parametric t-SNE to reflect the characteristics of high-dimensional quantum data on low-dimensional data. We use fidelity-based metrics instead of Euclidean distance in calculating high-dimensional data similarity. To verify our proposed method, we visualize both classical (Iris dataset) and quantum (time-depending Hamiltonian dynamics) data for classification tasks. Since this method allows us to represent a quantum dataset in a higher dimensional Hilbert space by a quantum dataset in a lower dimension while keeping their similarity, the proposed method can also be used to compress quantum data for further quantum machine learning.
t-distributed stochastic neighbor embedding (t-SNE) is a nonlinear dimensionality reduction algorithm that preserves local similarity by matching probability distributions between high- and low-dimensional spaces. Owing to its ability to capture complex manifold structures, t-SNE has become a widely used technique for high-dimensional data visualization. However, it still faces significant computational challenges when dealing with large-scale datasets. In this paper, we present a quantum-enhanced t-SNE algorithm that achieves a quadratic speedup with respect to the number of data samples. Specifically, three unitary operators are constructed using quantum arithmetic and comparators to compute the probability distributions. By integrating them with the Hadamard transform, the gradients of the Kullback-Leibler divergence can be efficiently computed. Moreover, since a complete quantum procedure is provided, our method surpasses the performance of existing quantum variants.
In quantum and quantum-inspired machine learning, a key step is to embed the data in the quantum space known as Hilbert space. Studying quantum kernel function, which defines the distances among the samples in the Hilbert space, belongs to the fundamental topics in this direction. In this work, we propose a tunable quantum-inspired kernel function (QIKF) named rescaled logarithmic fidelity (RLF) and a non-parametric algorithm for the semi-supervised learning in the quantum space. The rescaling takes advantage of the non-linearity of the kernel to tune the mutual distances of samples in the Hilbert space, and meanwhile avoids the exponentially-small fidelities between quantum many-qubit states. Being non-parametric excludes the possible effects from the variational parameters, and evidently demonstrates the properties of the kernel itself. Our results on the hand-written digits (MNIST dataset) and movie reviews (IMDb dataset) support the validity of our method, by comparing with the standard fidelity as the QIKF as well as several well-known non-parametric algorithms (naive Bayes classifiers, k-nearest neighbors, and spectral clustering). High accuracy is demonstrated, particularly for the unsupervised case with no labeled samples and the few-shot cases with small numbers of labeled samples. With the visualizations by t-stochastic neighbor embedding, our results imply that the machine learning in the Hilbert space complies with the principles of maximal coding rate reduction, where the low-dimensional data exhibit within-class compressibility, between-class discrimination, and overall diversity. The proposed QIKF and semi-supervised algorithm can be further combined with the parametric models such as tensor networks, quantum circuits, and quantum neural networks.
Classical machine learning algorithms can provide insights on high-dimensional processes that are hardly accessible with conventional approaches. As a notable example, t -distributed Stochastic Neighbor Embedding ( t -SNE) represents the state of the art for visualization of data sets of large dimensionality. An interesting question is then if this algorithm can provide useful information also in quantum experiments with very large Hilbert spaces. Leveraging these considerations, in this work we apply t -SNE to probe the spatial distribution of n -photon events in m -dimensional Hilbert spaces, showing that its findings can be beneficial for validating genuine quantum interference in boson sampling experiments. In particular, we find that nonlinear dimensionality reduction is capable to capture distinctive features in the spatial distribution of data related to multi-photon states with different evolutions. We envisage that this approach will inspire further theoretical investigations, for instance for a reliable assessment of quantum computational advantage.
We propose a novel quantum neural network architecture for unsupervised learning of classical and quantum data based on the kernelized version of Kohonen's self-organizing map. The central idea behind our algorithm is to replace the Euclidean distance metric with the fidelity between quantum states to identify the best matching unit from the low-dimensional grid of output neurons in the self-organizing map. The fidelities between the unknown quantum state and the quantum states containing the variational parameters are estimated by computing the transition probability on a quantum computer. The estimated fidelities are in turn used to adjust the variational parameters of the output neurons. Unlike O(N2)\mathcal{O}(N^{2})O(N2) circuit evaluations needed in quantum kernel estimation, our algorithm requires O(N)\mathcal{O}(N)O(N) circuit evaluations for NNN data samples. Analogous to the classical version of the self-organizing map, our algorithm learns a mapping from a high-dimensional Hilbert space to a low-dimensional grid of lattice points while preserving the underlying topology of the Hilbert space. We showcase the effectiveness of our algorithm by constructing a two-dimensional visualization that accurately differentiates between the three distinct species of flowers in Fisher's Iris dataset. In addition, we demonstrate the efficacy of our approach on quantum data by creating a two-dimensional map that preserves the topology of the state space in the Schwinger model and distinguishes between the two separate phases of the model at θ=πθ= πθ=π.
In quantum and quantum-inspired machine learning, the very first step is to embed the data in quantum space known as Hilbert space. Developing quantum kernel function (QKF), which defines the distances among the samples in the Hilbert space, belongs to the fundamental topics for machine learning. In this work, we propose the rescaled logarithmic fidelity (RLF) and a non-parametric active learning in the quantum space, which we name as RLF-NAL. The rescaling takes advantage of the non-linearity of the kernel to tune the mutual distances of samples in the Hilbert space, and meanwhile avoids the exponentially-small fidelities between quantum many-qubit states. We compare RLF-NAL with several well-known non-parametric algorithms including naive Bayes classifiers, kkk-nearest neighbors, and spectral clustering. Our method exhibits excellent accuracy particularly for the unsupervised case with no labeled samples and the few-shot cases with small numbers of labeled samples. With the visualizations by t-SNE, our results imply that the machine learning in the Hilbert space complies with the principles of maximal coding rate reduction, where the low-dimensional data exhibit within-class compressibility, between-class discrimination, and overall diversity. Our proposals can be applied to other quantum and quantum-inspired machine learning, including the methods using the parametric models such as tensor networks, quantum circuits, and quantum neural networks.
Quantum computing is expected to fundamentally change computer systems in the future. Recently, a new research topic of quantum computing is the hybrid quantum–classical approach for machine learning, in which a parameterized quantum circuit, also called quantum neural network (QNN), is optimized by a classical computer. This hybrid approach can have the benefits of both quantum computing and classical machine learning methods. In this early stage, it is of crucial importance to understand the new characteristics of quantum neural networks for different machine learning tasks. In this paper, we will study quantum neural networks for the task of classifying images, which are high-dimensional spatial data. In contrast to previous evaluations of low-dimensional or scalar data, we will investigate the impacts of practical encoding types, circuit depth, bias term, and readout on classification performance on the popular MNIST image dataset. Various interesting findings on learning behaviors of different QNNs are obtained through experimental results. To the best of our knowledge, this is the first work that considers various QNN aspects for image data.