CRISP: Correlation-Resilient Indexing via Subspace Partitioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dimitropoulos, Dimitris, Michalopoulos, Achilleas, Tsitsigkos, Dimitrios, Mamoulis, Nikos
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911488964296704
author Dimitropoulos, Dimitris
Michalopoulos, Achilleas
Tsitsigkos, Dimitrios
Mamoulis, Nikos
author_facet Dimitropoulos, Dimitris
Michalopoulos, Achilleas
Tsitsigkos, Dimitrios
Mamoulis, Nikos
contents As the dimensionality of modern learned representations increases to thousands of dimensions, the state-of-the-art Approximate Nearest Neighbor (ANN) indices exhibit severe limitations. Graph-based methods (e.g., HNSW) suffer from prohibitive memory consumption and routing degradation, while recent randomized quantization and learned rotation approaches (e.g., RaBitQ, OPQ) impose significant preprocessing overheads. We introduce CRISP, a novel framework designed for ANN search in very-high-dimensional spaces. Unlike rigid pipelines that apply expensive orthogonal rotations indiscriminately, CRISP employs a lightweight, correlation- aware adaptive strategy that redistributes variance only when necessary, effectively reducing the preprocessing complexity. We couple this adaptive mechanism with a cache-coherent Compressed Sparse Row (CSR) index structure. Furthermore, CRISP incorporates a multi-stage dual-mode query engine: a Guaranteed Mode that preserves rigorous theoretical lower bounds on recall, and an Optimized Mode that leverages rank-based weighted scoring and early termination to reduce query latency. Extensive evaluation on datasets of very high dimensionality (up to 4096) demonstrates that CRISP achieves state-of-the-art query throughput, low construction costs, and peak memory efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05180
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CRISP: Correlation-Resilient Indexing via Subspace Partitioning
Dimitropoulos, Dimitris
Michalopoulos, Achilleas
Tsitsigkos, Dimitrios
Mamoulis, Nikos
Databases
H.2.2
As the dimensionality of modern learned representations increases to thousands of dimensions, the state-of-the-art Approximate Nearest Neighbor (ANN) indices exhibit severe limitations. Graph-based methods (e.g., HNSW) suffer from prohibitive memory consumption and routing degradation, while recent randomized quantization and learned rotation approaches (e.g., RaBitQ, OPQ) impose significant preprocessing overheads. We introduce CRISP, a novel framework designed for ANN search in very-high-dimensional spaces. Unlike rigid pipelines that apply expensive orthogonal rotations indiscriminately, CRISP employs a lightweight, correlation- aware adaptive strategy that redistributes variance only when necessary, effectively reducing the preprocessing complexity. We couple this adaptive mechanism with a cache-coherent Compressed Sparse Row (CSR) index structure. Furthermore, CRISP incorporates a multi-stage dual-mode query engine: a Guaranteed Mode that preserves rigorous theoretical lower bounds on recall, and an Optimized Mode that leverages rank-based weighted scoring and early termination to reduce query latency. Extensive evaluation on datasets of very high dimensionality (up to 4096) demonstrates that CRISP achieves state-of-the-art query throughput, low construction costs, and peak memory efficiency.
title CRISP: Correlation-Resilient Indexing via Subspace Partitioning
topic Databases
H.2.2
url https://arxiv.org/abs/2603.05180