Live intelligence

Latest AI updates

1 updates
Research

e-means clustering claims faster convergence than Lloyd's k-means

Researchers introduce e-means, a mini-batch k-means procedure using an exponential moving average optimization scheme and scaling laws for decay rate and batch size. The paper reports that e-means reaches Lloyd k-means' 25-epoch loss in 1.4 to 2.6 epochs across embedding datasets, yielding claimed 10-45x GPU wall-clock speedups. It also reports partitioning 10 billion DINO embeddings into 16 million clusters in 2.5 epochs. The method is positioned for clustering, retrieval, quantization and data curation workloads.

clusteringembedding datasetsunsupervised learning