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:2504.20982

Provably faster randomized and quantum algorithms for $k$-means clustering via uniform sampling

Tyler Chen, Archan Ray, Akshay Seshadri, Dylan Herman, Bao Bach, Pranav Deshpande, Som, Abhishek, Niraj Kumar, Marco Pistoia

Published Apr 29, 2025• 0 citations
arXivHTMLPDF

Abstract

The $k$-means algorithm (Lloyd's algorithm) is a widely used method for clustering unlabeled data. A key bottleneck of the $k$-means algorithm is that each iteration requires time linear in the number of data points, which can be expensive in big data applications. This was improved in recent works proposing quantum and quantum-inspired classical algorithms to approximate the $k$-means algorithm locally, in time depending only logarithmically on the number of data points (along with data dependent parameters) [q-means: A quantum algorithm for unsupervised machine learning, Kerenidis, Landman, Luongo, and Prakash, NeurIPS 2019; Do you know what $q$-means?, Cornelissen, Doriguello, Luongo, Tang, QTML 2025]. In this work, we describe a simple randomized mini-batch $k$-means algorithm and a quantum algorithm inspired by the classical algorithm. We demonstrate that the worst case guarantees of these algorithms can significantly improve upon the bounds for algorithms in prior work. Our improvements are due to a careful use of uniform sampling, which preserves certain symmetries of the $k$-means problem that are not preserved in previous algorithms that use data norm-based sampling.

DOI
10.48550/arxiv.2504.20982

Related papers

Do you know what q-means?

Arjan Cornelissen, João Fernando Doriguello, Alessandro Luongo +1 more

Clustering is one of the most important tools for analysis of large datasets, and perhaps the most popular clustering algorithm is Lloyd's algorithm for $k$-means. This algorithm takes $n$ vectors $V=[v_1,\dots,v_n]\in\mathbb{R}^{d\times n}$ and outputs $k$ centroids $c_1,\dots,c_k\in\mathbb{R}^d$; these partition the vectors into clusters based on which centroid is closest to a particular vector. We present a classical $\varepsilon$-$k$-means algorithm that performs an approximate version of one iteration of Lloyd's algorithm with time complexity $\tilde{O}\big(\frac{\|V\|_F^2}{n}\frac{k^{2}d}{\varepsilon^2}(k + \log{n})\big)$, exponentially improving the dependence on the data size $n$ and matching that of the "$q$-means" quantum algorithm originally proposed by Kerenidis, Landman, Luongo, and Prakash (NeurIPS'19). Moreover, we propose an improved $q$-means quantum algorithm with time complexity $\tilde{O}\big(\frac{\|V\|_F}{\sqrt{n}}\frac{k^{3/2}d}{\varepsilon}(\sqrt{k}+\sqrt{d})(\sqrt{k} + \log{n})\big)$ that quadratically improves the runtime of our classical $\varepsilon$-$k$-means algorithm in several parameters. Our quantum algorithm does not rely on quantum linear algebra primitives of prior work, but instead only uses QRAM to prepare simple states based on the current iteration's clusters and multivariate quantum amplitude estimation. Finally, we provide classical and quantum query lower bounds, showing that our algorithms are optimal in most parameters.

arXiv:2308.09701•Aug 18, 2023•2 citations

Quantum expectation-maximization algorithm

Hideyuki Miyahara, Kazuyuki Aihara, Wolfgang Lechner

Clustering algorithms are a cornerstone of machine learning applications. Recently, a quantum algorithm for clustering based on the $k$-means algorithm has been proposed by Kerenidis, Landman, Luongo, and Prakash. Based on their work, we propose a quantum expectation-maximization algorithm for Gaussian mixture models (GMMs). The robustness and quantum speedup of the algorithm are shown. We also show numerically the advantage of GMM over $k$-means algorithm for nontrivial cluster data.

arXiv:1908.06655•Physical Review A•Jan 17, 2020•14 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

A Quantum Approximation Scheme for k-Means

Ragesh Jaiswal

We give a quantum approximation scheme (i.e., $(1 + \varepsilon)$-approximation for every $\varepsilon > 0$) for the classical $k$-means clustering problem in the QRAM model with a running time that has only polylogarithmic dependence on the number of data points. More specifically, given a dataset $V$ with $N$ points in $\mathbb{R}^d$ stored in QRAM data structure, our quantum algorithm runs in time $\tilde{O} \left( 2^{\tilde{O}(\frac{k}{\varepsilon})} η^2 d\right)$ and with high probability outputs a set $C$ of $k$ centers such that $cost(V, C) \leq (1+\varepsilon) \cdot cost(V, C_{OPT})$. Here $C_{OPT}$ denotes the optimal $k$-centers, $cost(.)$ denotes the standard $k$-means cost function (i.e., the sum of the squared distance of points to the closest center), and $η$ is the aspect ratio (i.e., the ratio of maximum distance to minimum distance). This is the first quantum algorithm with a polylogarithmic running time that gives a provable approximation guarantee of $(1+\varepsilon)$ for the $k$-means problem. Also, unlike previous works on unsupervised learning, our quantum algorithm does not require quantum linear algebra subroutines and has a running time independent of parameters (e.g., condition number) that appear in such procedures.

arXiv:2308.08167•Aug 16, 2023•3 citations

Novel Enhanced Unsupervised Quantum Clustering Algorithm

Diptanshu Sikdar, Joe Clapis, Swetha Bhattacharya

Every day, humans generate approximately 2.5 billion gigabytes of new data. While this data is crucial in applications such as drug development and cybersecurity, it is mostly unstructured and unlabeled which makes it difficult to process effectively. Businesses and governments alike solve this problem by using machine learning algorithms to characterize the data and make decisions with it. However, conventional machine learning processes consume excessive computational resources and time: one of the most prominent, K-means clustering, has an approximate time complexity of O(n^2), where n is the input data size. This quadratic time complexity causes scalability problems with large datasets. In this project, I have created an improved, more scalable clustering algorithm by leveraging quantum computation. The approach (new Q-means) involves an Angle Embedding Feature Map, an d-dimensional SWAP Test, and a dynamic, threshold distance-based termination criteria. After implementing this algorithm using the IBM Qiskit SDK, the new Q-means algorithm was run several times on different dimensional datasets. On an average, the new Q-means performed 18% better than the K-means algorithm based on the Adjusted Rand Index. In terms of the simulation execution time, the new Q-means was about six times faster than the existing Q-means due to a multi-threaded implementation and faster convergence. The time complexity of the new Q-means without a Quantum Random Access Memory (QRAM) is O(n^2). While the existing Q-means algorithm, which utilizes QRAM, has a time complexity of O(n(log n)^p), the time complexity of the new Q-means with QRAM is significantly better—O(n).

Journal of Student Research•May 31, 2022•0 citations
Provably faster randomized and quantum algorithms for kkk-means clustering via uniform sampling
The kkk-means algorithm (Lloyd's algorithm) is a widely used method for clustering unlabeled data. A key bottleneck of the kkk-means algorithm is that each iteration requires time linear in the number of data points, which can be expensive in big data applications. This was improved in recent works proposing quantum and quantum-inspired classical algorithms to approximate the kkk-means algorithm locally, in time depending only logarithmically on the number of data points (along with data dependent parameters) [q-means: A quantum algorithm for unsupervised machine learning, Kerenidis, Landman, Luongo, and Prakash, NeurIPS 2019; Do you know what qqq-means?, Cornelissen, Doriguello, Luongo, Tang, QTML 2025]. In this work, we describe a simple randomized mini-batch kkk-means algorithm and a quantum algorithm inspired by the classical algorithm. We demonstrate that the worst case guarantees of these algorithms can significantly improve upon the bounds for algorithms in prior work. Our improvements are due to a careful use of uniform sampling, which preserves certain symmetries of the kkk-means problem that are not preserved in previous algorithms that use data norm-based sampling.
Clustering is one of the most important tools for analysis of large datasets, and perhaps the most popular clustering algorithm is Lloyd's algorithm for kkk-means. This algorithm takes nnn vectors V=[v1,…,vn]∈Rd×nV=[v_1,\dots,v_n]\in\mathbb{R}^{d\times n}V=[v1​,…,vn​]∈Rd×n and outputs kkk centroids c1,…,ck∈Rdc_1,\dots,c_k\in\mathbb{R}^dc1​,…,ck​∈Rd; these partition the vectors into clusters based on which centroid is closest to a particular vector. We present a classical ε\varepsilonε-kkk-means algorithm that performs an approximate version of one iteration of Lloyd's algorithm with time complexity O~(∥V∥F2nk2dε2(k+log⁡n))\tilde{O}\big(\frac{\|V\|_F^2}{n}\frac{k^{2}d}{\varepsilon^2}(k + \log{n})\big)O~(n∥V∥F2​​ε2k2d​(k+logn)), exponentially improving the dependence on the data size nnn and matching that of the "qqq-means" quantum algorithm originally proposed by Kerenidis, Landman, Luongo, and Prakash (NeurIPS'19). Moreover, we propose an improved qqq-means quantum algorithm with time complexity O~(∥V∥Fnk3/2dε(k+d)(k+log⁡n))\tilde{O}\big(\frac{\|V\|_F}{\sqrt{n}}\frac{k^{3/2}d}{\varepsilon}(\sqrt{k}+\sqrt{d})(\sqrt{k} + \log{n})\big)O~(n​∥V∥F​​εk3/2d​(k​+d​)(k​+logn)) that quadratically improves the runtime of our classical ε\varepsilonε-kkk-means algorithm in several parameters. Our quantum algorithm does not rely on quantum linear algebra primitives of prior work, but instead only uses QRAM to prepare simple states based on the current iteration's clusters and multivariate quantum amplitude estimation. Finally, we provide classical and quantum query lower bounds, showing that our algorithms are optimal in most parameters.
Clustering algorithms are a cornerstone of machine learning applications. Recently, a quantum algorithm for clustering based on the kkk-means algorithm has been proposed by Kerenidis, Landman, Luongo, and Prakash. Based on their work, we propose a quantum expectation-maximization algorithm for Gaussian mixture models (GMMs). The robustness and quantum speedup of the algorithm are shown. We also show numerically the advantage of GMM over kkk-means algorithm for nontrivial cluster data.
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.
We give a quantum approximation scheme (i.e., (1+ε)(1 + \varepsilon)(1+ε)-approximation for every ε>0\varepsilon > 0ε>0) for the classical kkk-means clustering problem in the QRAM model with a running time that has only polylogarithmic dependence on the number of data points. More specifically, given a dataset VVV with NNN points in Rd\mathbb{R}^dRd stored in QRAM data structure, our quantum algorithm runs in time O~(2O~(kε)η2d)\tilde{O} \left( 2^{\tilde{O}(\frac{k}{\varepsilon})} η^2 d\right)O~(2O~(εk​)η2d) and with high probability outputs a set CCC of kkk centers such that cost(V,C)≤(1+ε)⋅cost(V,COPT)cost(V, C) \leq (1+\varepsilon) \cdot cost(V, C_{OPT})cost(V,C)≤(1+ε)⋅cost(V,COPT​). Here COPTC_{OPT}COPT​ denotes the optimal kkk-centers, cost(.)cost(.)cost(.) denotes the standard kkk-means cost function (i.e., the sum of the squared distance of points to the closest center), and ηηη is the aspect ratio (i.e., the ratio of maximum distance to minimum distance). This is the first quantum algorithm with a polylogarithmic running time that gives a provable approximation guarantee of (1+ε)(1+\varepsilon)(1+ε) for the kkk-means problem. Also, unlike previous works on unsupervised learning, our quantum algorithm does not require quantum linear algebra subroutines and has a running time independent of parameters (e.g., condition number) that appear in such procedures.
Every day, humans generate approximately 2.5 billion gigabytes of new data. While this data is crucial in applications such as drug development and cybersecurity, it is mostly unstructured and unlabeled which makes it difficult to process effectively. Businesses and governments alike solve this problem by using machine learning algorithms to characterize the data and make decisions with it. However, conventional machine learning processes consume excessive computational resources and time: one of the most prominent, K-means clustering, has an approximate time complexity of O(n^2), where n is the input data size. This quadratic time complexity causes scalability problems with large datasets. In this project, I have created an improved, more scalable clustering algorithm by leveraging quantum computation. The approach (new Q-means) involves an Angle Embedding Feature Map, an d-dimensional SWAP Test, and a dynamic, threshold distance-based termination criteria. After implementing this algorithm using the IBM Qiskit SDK, the new Q-means algorithm was run several times on different dimensional datasets. On an average, the new Q-means performed 18% better than the K-means algorithm based on the Adjusted Rand Index. In terms of the simulation execution time, the new Q-means was about six times faster than the existing Q-means due to a multi-threaded implementation and faster convergence. The time complexity of the new Q-means without a Quantum Random Access Memory (QRAM) is O(n^2). While the existing Q-means algorithm, which utilizes QRAM, has a time complexity of O(n(log n)^p), the time complexity of the new Q-means with QRAM is significantly better—O(n).