A Quantum Approximation Scheme for k-Means

We give a quantum approximation scheme (i.e., -approximation for every ) for the classical -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 with points in stored in QRAM data structure, our quantum algorithm runs in time and with high probability outputs a set of centers such that . Here denotes the optimal -centers, denotes the standard -means cost function (i.e., the sum of the squared distance of points to the closest center), and 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 for the -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.
View on arXiv