A statistical risk estimation method enables query-specific dimension selection in dense embeddings, achieving equivalent effectiveness with about 50% smaller embeddings at inference time.
InProceedings of the Thirteenth Text REtrieval Conference (TREC 2004), Gaithersburg, MD
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Statistical Foundations of DIME: Risk Estimation for Practical Index Selection
A statistical risk estimation method enables query-specific dimension selection in dense embeddings, achieving equivalent effectiveness with about 50% smaller embeddings at inference time.