IVF-TQ replaces learned codebooks with a fixed random rotation and precomputed scalar quantizer in the residual layer of an IVF index, delivering streaming recall stability at fixed bit budgets via a uniform-over-sphere inner-product bound.
2018.High-Dimensional Probability: An Introduction with Applications in Data Science
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
MCI approximates dense nearest neighbor graphs via maximal clique covers and progressive local densification to support fast arbitrary-filtered approximate nearest neighbor search with reduced space.
Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.
Fragment classification is efficiently learnable by quantum neural networks under suitable conditions but resists known classical dequantization techniques.
citing papers explorer
-
IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer
IVF-TQ replaces learned codebooks with a fixed random rotation and precomputed scalar quantizer in the residual layer of an IVF index, delivering streaming recall stability at fixed bit budgets via a uniform-over-sphere inner-product bound.
-
MCI: A Maximal Clique Index for Efficient Arbitrary-Filtered Approximate Nearest Neighbor Search
MCI approximates dense nearest neighbor graphs via maximal clique covers and progressive local densification to support fast arbitrary-filtered approximate nearest neighbor search with reduced space.
-
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
Injecting a few malicious vectors near the centroid exploits centrality-driven hubness in high-dimensional embeddings, causing them to dominate top-k retrievals in up to 99.85% of cases.
-
Fragmentation is Efficiently Learnable by Quantum Neural Networks
Fragment classification is efficiently learnable by quantum neural networks under suitable conditions but resists known classical dequantization techniques.