Medoids in almost linear time via multi-armed bandits
Machine Learning
2017-11-08 v3 Data Structures and Algorithms
Information Theory
Machine Learning
math.IT
Abstract
Computing the medoid of a large number of points in high-dimensional space is an increasingly common operation in many data science problems. We present an algorithm Med-dit which uses O(n log n) distance evaluations to compute the medoid with high probability. Med-dit is based on a connection with the multi-armed bandit problem. We evaluate the performance of Med-dit empirically on the Netflix-prize and the single-cell RNA-Seq datasets, containing hundreds of thousands of points living in tens of thousands of dimensions, and observe a 5-10x improvement in performance over the current state of the art. Med-dit is available at https://github.com/bagavi/Meddit
Cite
@article{arxiv.1711.00817,
title = {Medoids in almost linear time via multi-armed bandits},
author = {Vivek Bagaria and Govinda M. Kamath and Vasilis Ntranos and Martin J. Zhang and David Tse},
journal= {arXiv preprint arXiv:1711.00817},
year = {2017}
}