3 papers
cs.LG2026
A Super Fast K-means for Indexing Vector Embeddings
Leonardo Kuffo, Sven Hepkema, Peter Boncz
We present SuperKMeans: a k-means variant designed for clustering collections of high-dimensional vector embeddings. SuperKMeans' clustering is up to 7x faster than FAISS and Sciki…
cs.DB2025
Bang for the Buck: Vector Search on Cloud CPUs
Leonardo Kuffo, Peter Boncz
Vector databases have emerged as a new type of systems that support efficient querying of high-dimensional vectors. Many of these offer their database as a service in the cloud. Ho…
cs.DB2025
PDX: A Data Layout for Vector Similarity Search
Leonardo Kuffo, Elena Krippner, Peter Boncz
We propose Partition Dimensions Across (PDX), a data layout for vectors (e.g., embeddings) that, similar to PAX [6], stores multiple vectors in one block, using a vertical layout f…