e-means: outperforming k-means (in one-tenth the epochs)

A paper introducing e-means, an exponential moving average optimization procedure for k-means with mini-batch updates built on modern deep learning machinery, reports that it outperforms Lloyd's k-means algorithm in one-tenth the epochs. Lloyd's k-means has long been a standard for clustering used in data analysis, retrieval, quantization and data curation. The paper positions e-means as a faster-converging alternative for those clustering workloads.

Lloyd's k-means algorithm is a long-running standard for clustering, with applications in data analysis, retrieval, quantization and data curation. In this paper, we introduce an exponential moving average optimization procedure for k-means with mini-batch updates, powered by modern deep learning ma