q-means: A quantum algorithm for unsupervised machine learning

by   Iordanis Kerenidis, et al.

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 ∈R^N × d) stored in QRAM, the running time of q-means is O( k d η/δ^2κ(V)(μ(V) + k η/δ) + k^2 η^1.5/δ^2κ(V)μ(V) ) per iteration, where κ(V) is the condition number, μ(V) is a parameter that appears in quantum linear algebra procedures and η = _i ||v_i||^2. For a natural notion of well-clusterable datasets, the running time becomes O( k^2 d η^2.5/δ^3 + k^2.5η^2/δ^3) 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.


page 1

page 2

page 3

page 4


A Quantum Approximation Scheme for k-Means

We give a quantum approximation scheme (i.e., (1 + ε)-approximation for ...

Do you know what q-means?

Clustering is one of the most important tools for analysis of large data...

Quantum algorithms for feedforward neural networks

Quantum machine learning has the potential for broad industrial applicat...

Quantum Unsupervised and Supervised Learning on Superconducting Processors

Machine learning algorithms perform well on identifying patterns in many...

Balanced k-Means Clustering on an Adiabatic Quantum Computer

Adiabatic quantum computers are a promising platform for approximately s...

Quantum classification of the MNIST dataset via Slow Feature Analysis

Quantum machine learning carries the promise to revolutionize informatio...

A Quantum Interior Point Method for LPs and SDPs

We present a quantum interior point method with worst case running time ...

Please sign up or login with your details

Forgot password? Click here to reset