A statistical risk estimation method enables query-specific dimension selection in dense embeddings, achieving equivalent effectiveness with about 50% smaller embeddings at inference time.
We can see that if we let the kernel weights to be uniform, the serieslimM→∞ PM i=1 σ2 i M 2 does not converge
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.