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:2007.00280 · Physical Review A

Quantum spectral clustering

Iordanis Kerenidis, Jonas Landman

Published Apr 15, 2021• 68 citations
arXivHTMLPDF

Abstract

Spectral clustering is a powerful unsupervised machine learning algorithm for clustering data with nonconvex or nested structures [A. Y. Ng, M. I. Jordan, and Y. Weiss, On spectral clustering: Analysis and an algorithm, in Advances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference (MIT Press, Cambridge, MA, 2002), pp. 849--856]. With roots in graph theory, it uses the spectral properties of the Laplacian matrix to project the data in a low-dimensional space where clustering is more efficient. Despite its success in clustering tasks, spectral clustering suffers in practice from a fast-growing running time of $O({n}^{3})$, where $n$ is the number of points in the data set. In this work we propose an end-to-end quantum algorithm performing spectral clustering, extending a number of works in quantum machine learning. The quantum algorithm is composed of two parts: the first is the efficient creation of the quantum state corresponding to the projected Laplacian matrix, and the second consists of applying the existing quantum analog of the $k$-means algorithm [I. Kerenidis, J. Landman, A. Luongo, and A. Prakash, $q$-means: A quantum algorithm for unsupervised machine learning, in Advances in Neural Information Processing Systems 32: Proceedings of the 2019 Conference (Curran Associates, Red Hook, NY, 2020), pp. 4136--4146]. Both steps depend polynomially on the number of clusters, as well as precision and data parameters arising from quantum procedures, and polylogarithmically on the dimension of the input vectors. Our numerical simulations show an asymptotic linear growth with $n$ when all terms are taken into account, significantly better than the classical cubic growth. This work opens the path to other graph-based quantum machine learning algorithms, as it provides routines for efficient computation and quantum access to the incidence, adjacency, and projected Laplacian matrices of a graph.

DOI
10.1103/physreva.103.042415

Related papers

Quantum Spectral Clustering of Mixed Graphs

Daniel Volya, Prabhat Mishra

Spectral graph partitioning is a well known technique to estimate clusters in undirected graphs. Recent approaches explored efficient spectral algorithms for directed and mixed graphs utilizing various matrix representations. Despite its success in clustering tasks, classical spectral algorithms suffer from a cubic growth in runtime. In this paper, we propose a quantum spectral clustering algorithm for discovering clusters and properties of mixed graphs. Our experimental results based on numerical simulations demonstrate that our quantum spectral clustering outperforms classical spectral clustering techniques. Specifically, our approach leads to a linear growth in complexity, while state-of-the-art classical counterpart leads to cubic growth. In a case study, we apply our proposed algorithm to preform unsupervised machine learning using both real and simulated quantum computers. This work opens an avenue for efficient implementation of machine learning algorithms on directed as well as mixed graphs by making use of the inherent potential quantum speedup.

ACM/IEEE Design Automation Conference (DAC)•Nov 8, 2021•13 citations

Quantum Algorithm for Regularized Spectral Clustering

Changzhou Long, Yasunori Futamura, Xiucai Ye +1 more

Spectral clustering is one of the most robust methods of an unsupervised machine learning field. Compared with the well-known k-means, spectral clustering uses the spectral properties of the Laplacian matrix to project data to a low-dimensional clustering with higher efficiency. However, for a sparse network with a substantial degree of heterogeneity, standard spectral clustering often overfits noise in the periphery of a sparse and stochastic graph. In our work, we combined the quantum version of the k-means algorithm with regularized spectral clustering and proposed a new quantum machine learning algorithm. It is more like a combination of classical and quantum algorithms. Compared with the established quantum k-means algorithm, our method has obvious computational advantages in non-convex or nested structures. At this stage, the research of quantum algorithms mainly stays in the simulation of classical computers. Our method does not need to expend a lot of effort to preprocess the data at the initial quantum state stage. Under the assumption of quantum data encoding, we theoretically demonstrate the feasibility of the quantum regularized spectral clustering algorithm. Then combine Q-means algorithm complexity advantages to complete the clustering task. This work aims to pave the path and help realize quantum spectral clustering algorithms on real quantum computers in the future and help create other versions of quantum machine learning algorithms. We provide simulations and data examples to illustrate these results.

International Conference on Machine Learning and Computing (ICMLC)•Feb 17, 2023•2 citations

q-means: A quantum algorithm for unsupervised machine learning

Iordanis Kerenidis, Jonas Landman, Alessandro Luongo +1 more

Quantum machine learning is one of the most promising applications of a full-scale quantum computer. Over the past few years, many quantum machine learning algorithms have been proposed that can potentially offer considerable speedups over the corresponding classical algorithms. In this paper, we introduce q-means, a new quantum algorithm for clustering which is a canonical problem in unsupervised machine learning. The $q$-means algorithm has convergence and precision guarantees similar to $k$-means, and it outputs with high probability a good approximation of the $k$ cluster centroids like the classical algorithm. Given a dataset of $N$ $d$-dimensional vectors $v_i$ (seen as a matrix $V \in \mathbb{R}^{N \times d})$ stored in QRAM, the running time of q-means is $\widetilde{O}\left( k d \fracη{δ^2}κ(V)(μ(V) + k \fracηδ) + k^2 \frac{η^{1.5}}{δ^2} κ(V)μ(V) \right)$ per iteration, where $κ(V)$ is the condition number, $μ(V)$ is a parameter that appears in quantum linear algebra procedures and $η= \max_{i} ||v_{i}||^{2}$. For a natural notion of well-clusterable datasets, the running time becomes $\widetilde{O}\left( k^2 d \frac{η^{2.5}}{δ^3} + k^{2.5} \frac{η^2}{δ^3} \right)$ per iteration, which is linear in the number of features $d$, and polynomial in the rank $k$, the maximum square norm $η$ and the error parameter $δ$. Both running times are only polylogarithmic in the number of datapoints $N$. Our algorithm provides substantial savings compared to the classical $k$-means algorithm that runs in time $O(kdN)$ per iteration, particularly for the case of large datasets.

arXiv:1812.03584•Dec 10, 2018•119 citations

q-means: A quantum algorithm for unsupervised machine learning

Iordanis Kerenidis, Jonas Landman, Alessandro Luongo +1 more

Quantum machine learning is one of the most promising applications of a full-scale quantum computer. Over the past few years, many quantum machine learning algorithms have been proposed that can potentially offer considerable speedups over the corresponding classical algorithms. In this paper, we introduce q-means, a new quantum algorithm for clustering which is a canonical problem in unsupervised machine learning. The $q$-means algorithm has convergence and precision guarantees similar to $k$-means, and it outputs with high probability a good approximation of the $k$ cluster centroids like the classical algorithm. Given a dataset of $N$ $d$-dimensional vectors $v_i$ (seen as a matrix $V \in \mathbb{R}^{N \times d})$ stored in QRAM, the running time of q-means is $\widetilde{O}\left( k d \frac{\eta}{\delta^2}\kappa(V)(\mu(V) + k \frac{\eta}{\delta}) + k^2 \frac{\eta^{1.5}}{\delta^2} \kappa(V)\mu(V) \right)$ per iteration, where $\kappa(V)$ is the condition number, $\mu(V)$ is a parameter that appears in quantum linear algebra procedures and $\eta = \max_{i} ||v_{i}||^{2}$. For a natural notion of well-clusterable datasets, the running time becomes $\widetilde{O}\left( k^2 d \frac{\eta^{2.5}}{\delta^3} + k^{2.5} \frac{\eta^2}{\delta^3} \right)$ per iteration, which is linear in the number of features $d$, and polynomial in the rank $k$, the maximum square norm $\eta$ and the error parameter $\delta$. Both running times are only polylogarithmic in the number of datapoints $N$. Our algorithm provides substantial savings compared to the classical $k$-means algorithm that runs in time $O(kdN)$ per iteration, particularly for the case of large datasets.

•Jan 1, 2019•15 citations

Quantum Algorithms for Unsupervised Machine Learning and Neural Networks

Jonas Landman

In this thesis, we investigate whether quantum algorithms can be used in the field of machine learning for both long and near term quantum computers. We will first recall the fundamentals of machine learning and quantum computing and then describe more precisely how to link them through linear algebra: we introduce quantum algorithms to efficiently solve tasks such as matrix product or distance estimation. These results are then used to develop new quantum algorithms for unsupervised machine learning, such as k-means and spectral clustering. This allows us to define many fundamental procedures, in particular in vector and graph analysis. We will also present new quantum algorithms for neural networks, or deep learning. For this, we introduce an algorithm to perform a quantum convolution product on images, as well as a new way to perform a fast tomography on quantum states. We prove that these quantum algorithms are faster versions of equivalent classical algorithms, but exhibit random effects due to the quantum nature of the computation. Many simulations have been carried out to study these effects and measure their learning accuracy on real data. Finally, we will present a quantum orthogonal neural network circuit adapted to the currently available small and imperfect quantum computers. This allows us to perform real experiments to test our theory.

arXiv:2111.03598•Nov 5, 2021•0 citations

Accelerating spectral clustering on quantum and analog platforms

Xingzi Xu, Tuhin Sahai

We introduce a novel hybrid quantum–analog algorithm to perform a graph clustering that exploits connections between the evolution of dynamical systems on graphs and the underlying graph spectra. This approach constitutes a new class of algorithms that combine emerging quantum and analog platforms to accelerate computations. Our hybrid algorithm is equivalent to spectral clustering and significantly reduces the computational complexity from 𝒪(N3) to 𝒪(N), where N is the number of nodes in the graph. We achieve this speedup by circumventing the need for explicit eigendecomposition of the normalized graph Laplacian matrix, which dominates the classical complexity, and instead leveraging quantum evolution of the Schrödinger equation followed by efficient analog computation for the dynamic mode decomposition (DMD) step. Specifically, while classical spectral clustering requires 𝒪(N3) operations to perform eigendecomposition, our method exploits the natural quantum evolution of states according to the graph Laplacian Hamiltonian in linear time, combined with the linear scaling for DMD that leverages efficient matrix–vector multiplications on analog hardware. We prove and demonstrate that this hybrid approach can extract the eigenvalues and scaled eigenvectors of the normalized graph Laplacian by evolving Schrödinger dynamics on quantum computers followed by DMD computations on analog devices, providing a significant computational advantage for large-scale graph clustering problems. Our demonstrations can be reproduced using our code that has been released at on github.

arXiv:2408.08486•Academia quantum.•Mar 24, 2025•2 citations
Spectral clustering is a powerful unsupervised machine learning algorithm for clustering data with nonconvex or nested structures [A. Y. Ng, M. I. Jordan, and Y. Weiss, On spectral clustering: Analysis and an algorithm, in Advances in Neural Information Processing Systems 14: Proceedings of the 2001 Conference (MIT Press, Cambridge, MA, 2002), pp. 849--856]. With roots in graph theory, it uses the spectral properties of the Laplacian matrix to project the data in a low-dimensional space where clustering is more efficient. Despite its success in clustering tasks, spectral clustering suffers in practice from a fast-growing running time of O(n3)O({n}^{3})O(n3), where nnn is the number of points in the data set. In this work we propose an end-to-end quantum algorithm performing spectral clustering, extending a number of works in quantum machine learning. The quantum algorithm is composed of two parts: the first is the efficient creation of the quantum state corresponding to the projected Laplacian matrix, and the second consists of applying the existing quantum analog of the kkk-means algorithm [I. Kerenidis, J. Landman, A. Luongo, and A. Prakash, qqq-means: A quantum algorithm for unsupervised machine learning, in Advances in Neural Information Processing Systems 32: Proceedings of the 2019 Conference (Curran Associates, Red Hook, NY, 2020), pp. 4136--4146]. Both steps depend polynomially on the number of clusters, as well as precision and data parameters arising from quantum procedures, and polylogarithmically on the dimension of the input vectors. Our numerical simulations show an asymptotic linear growth with nnn when all terms are taken into account, significantly better than the classical cubic growth. This work opens the path to other graph-based quantum machine learning algorithms, as it provides routines for efficient computation and quantum access to the incidence, adjacency, and projected Laplacian matrices of a graph.
Spectral graph partitioning is a well known technique to estimate clusters in undirected graphs. Recent approaches explored efficient spectral algorithms for directed and mixed graphs utilizing various matrix representations. Despite its success in clustering tasks, classical spectral algorithms suffer from a cubic growth in runtime. In this paper, we propose a quantum spectral clustering algorithm for discovering clusters and properties of mixed graphs. Our experimental results based on numerical simulations demonstrate that our quantum spectral clustering outperforms classical spectral clustering techniques. Specifically, our approach leads to a linear growth in complexity, while state-of-the-art classical counterpart leads to cubic growth. In a case study, we apply our proposed algorithm to preform unsupervised machine learning using both real and simulated quantum computers. This work opens an avenue for efficient implementation of machine learning algorithms on directed as well as mixed graphs by making use of the inherent potential quantum speedup.
Spectral clustering is one of the most robust methods of an unsupervised machine learning field. Compared with the well-known k-means, spectral clustering uses the spectral properties of the Laplacian matrix to project data to a low-dimensional clustering with higher efficiency. However, for a sparse network with a substantial degree of heterogeneity, standard spectral clustering often overfits noise in the periphery of a sparse and stochastic graph. In our work, we combined the quantum version of the k-means algorithm with regularized spectral clustering and proposed a new quantum machine learning algorithm. It is more like a combination of classical and quantum algorithms. Compared with the established quantum k-means algorithm, our method has obvious computational advantages in non-convex or nested structures. At this stage, the research of quantum algorithms mainly stays in the simulation of classical computers. Our method does not need to expend a lot of effort to preprocess the data at the initial quantum state stage. Under the assumption of quantum data encoding, we theoretically demonstrate the feasibility of the quantum regularized spectral clustering algorithm. Then combine Q-means algorithm complexity advantages to complete the clustering task. This work aims to pave the path and help realize quantum spectral clustering algorithms on real quantum computers in the future and help create other versions of quantum machine learning algorithms. We provide simulations and data examples to illustrate these results.
Quantum machine learning is one of the most promising applications of a full-scale quantum computer. Over the past few years, many quantum machine learning algorithms have been proposed that can potentially offer considerable speedups over the corresponding classical algorithms. In this paper, we introduce q-means, a new quantum algorithm for clustering which is a canonical problem in unsupervised machine learning. The qqq-means algorithm has convergence and precision guarantees similar to kkk-means, and it outputs with high probability a good approximation of the kkk cluster centroids like the classical algorithm. Given a dataset of NNN ddd-dimensional vectors viv_ivi​ (seen as a matrix V∈RN×d)V \in \mathbb{R}^{N \times d})V∈RN×d) stored in QRAM, the running time of q-means is O~(kdηδ2κ(V)(μ(V)+kηδ)+k2η1.5δ2κ(V)μ(V))\widetilde{O}\left( k d \fracη{δ^2}κ(V)(μ(V) + k \fracηδ) + k^2 \frac{η^{1.5}}{δ^2} κ(V)μ(V) \right)O(kdδ2η​κ(V)(μ(V)+kδη​)+k2δ2η1.5​κ(V)μ(V)) per iteration, where κ(V)κ(V)κ(V) is the condition number, μ(V)μ(V)μ(V) is a parameter that appears in quantum linear algebra procedures and η=max⁡i∣∣vi∣∣2η= \max_{i} ||v_{i}||^{2}η=maxi​∣∣vi​∣∣2. For a natural notion of well-clusterable datasets, the running time becomes O~(k2dη2.5δ3+k2.5η2δ3)\widetilde{O}\left( k^2 d \frac{η^{2.5}}{δ^3} + k^{2.5} \frac{η^2}{δ^3} \right)O(k2dδ3η2.5​+k2.5δ3η2​) per iteration, which is linear in the number of features ddd, and polynomial in the rank kkk, the maximum square norm ηηη and the error parameter δδδ. Both running times are only polylogarithmic in the number of datapoints NNN. Our algorithm provides substantial savings compared to the classical kkk-means algorithm that runs in time O(kdN)O(kdN)O(kdN) per iteration, particularly for the case of large datasets.
Quantum machine learning is one of the most promising applications of a full-scale quantum computer. Over the past few years, many quantum machine learning algorithms have been proposed that can potentially offer considerable speedups over the corresponding classical algorithms. In this paper, we introduce q-means, a new quantum algorithm for clustering which is a canonical problem in unsupervised machine learning. The qqq-means algorithm has convergence and precision guarantees similar to kkk-means, and it outputs with high probability a good approximation of the kkk cluster centroids like the classical algorithm. Given a dataset of NNN ddd-dimensional vectors viv_ivi​ (seen as a matrix V∈RN×d)V \in \mathbb{R}^{N \times d})V∈RN×d) stored in QRAM, the running time of q-means is O~(kdηδ2κ(V)(μ(V)+kηδ)+k2η1.5δ2κ(V)μ(V))\widetilde{O}\left( k d \frac{\eta}{\delta^2}\kappa(V)(\mu(V) + k \frac{\eta}{\delta}) + k^2 \frac{\eta^{1.5}}{\delta^2} \kappa(V)\mu(V) \right)O(kdδ2η​κ(V)(μ(V)+kδη​)+k2δ2η1.5​κ(V)μ(V)) per iteration, where κ(V)\kappa(V)κ(V) is the condition number, μ(V)\mu(V)μ(V) is a parameter that appears in quantum linear algebra procedures and η=max⁡i∣∣vi∣∣2\eta = \max_{i} ||v_{i}||^{2}η=maxi​∣∣vi​∣∣2. For a natural notion of well-clusterable datasets, the running time becomes O~(k2dη2.5δ3+k2.5η2δ3)\widetilde{O}\left( k^2 d \frac{\eta^{2.5}}{\delta^3} + k^{2.5} \frac{\eta^2}{\delta^3} \right)O(k2dδ3η2.5​+k2.5δ3η2​) per iteration, which is linear in the number of features ddd, and polynomial in the rank kkk, the maximum square norm η\etaη and the error parameter δ\deltaδ. Both running times are only polylogarithmic in the number of datapoints NNN. Our algorithm provides substantial savings compared to the classical kkk-means algorithm that runs in time O(kdN)O(kdN)O(kdN) per iteration, particularly for the case of large datasets.
In this thesis, we investigate whether quantum algorithms can be used in the field of machine learning for both long and near term quantum computers. We will first recall the fundamentals of machine learning and quantum computing and then describe more precisely how to link them through linear algebra: we introduce quantum algorithms to efficiently solve tasks such as matrix product or distance estimation. These results are then used to develop new quantum algorithms for unsupervised machine learning, such as k-means and spectral clustering. This allows us to define many fundamental procedures, in particular in vector and graph analysis. We will also present new quantum algorithms for neural networks, or deep learning. For this, we introduce an algorithm to perform a quantum convolution product on images, as well as a new way to perform a fast tomography on quantum states. We prove that these quantum algorithms are faster versions of equivalent classical algorithms, but exhibit random effects due to the quantum nature of the computation. Many simulations have been carried out to study these effects and measure their learning accuracy on real data. Finally, we will present a quantum orthogonal neural network circuit adapted to the currently available small and imperfect quantum computers. This allows us to perform real experiments to test our theory.
We introduce a novel hybrid quantum–analog algorithm to perform a graph clustering that exploits connections between the evolution of dynamical systems on graphs and the underlying graph spectra. This approach constitutes a new class of algorithms that combine emerging quantum and analog platforms to accelerate computations. Our hybrid algorithm is equivalent to spectral clustering and significantly reduces the computational complexity from 𝒪(N3) to 𝒪(N), where N is the number of nodes in the graph. We achieve this speedup by circumventing the need for explicit eigendecomposition of the normalized graph Laplacian matrix, which dominates the classical complexity, and instead leveraging quantum evolution of the Schrödinger equation followed by efficient analog computation for the dynamic mode decomposition (DMD) step. Specifically, while classical spectral clustering requires 𝒪(N3) operations to perform eigendecomposition, our method exploits the natural quantum evolution of states according to the graph Laplacian Hamiltonian in linear time, combined with the linear scaling for DMD that leverages efficient matrix–vector multiplications on analog hardware. We prove and demonstrate that this hybrid approach can extract the eigenvalues and scaled eigenvectors of the normalized graph Laplacian by evolving Schrödinger dynamics on quantum computers followed by DMD computations on analog devices, providing a significant computational advantage for large-scale graph clustering problems. Our demonstrations can be reproduced using our code that has been released at on github.