{"ID":2867998,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18471","arxiv_id":"2509.18471","title":"Individualized non-uniform quantization for vector search","abstract":"Embedding vectors are widely used for representing unstructured data and searching through it for semantically similar items. However, the large size of these vectors, due to their high-dimensionality, creates problems for modern vector search techniques: retrieving large vectors from memory/storage is expensive and their footprint is costly. In this work, we present NVQ (non-uniform vector quantization), a new vector compression technique that is computationally and spatially efficient in the high-fidelity regime. The core in NVQ is to use novel parsimonious and computationally efficient nonlinearities for building non-uniform vector quantizers. Critically, these quantizers are \\emph{individually} learned for each indexed vector. Our experimental results show that NVQ exhibits improved accuracy compared to the state of the art with a minimal computational cost.","short_abstract":"Embedding vectors are widely used for representing unstructured data and searching through it for semantically similar items. However, the large size of these vectors, due to their high-dimensionality, creates problems for modern vector search techniques: retrieving large vectors from memory/storage is expensive and th...","url_abs":"https://arxiv.org/abs/2509.18471","url_pdf":"https://arxiv.org/pdf/2509.18471v1","authors":"[\"Mariano Tepper\",\"Ted Willke\"]","published":"2025-09-22T23:20:07Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.IR\"]","methods":"[]","has_code":false}