Score: 0

Statistical Foundations of DIME: Risk Estimation for Practical Index Selection

Published: January 9, 2026 | arXiv ID: 2601.05649v1

By: Giulio D'Erasmo , Cesare Campagnano , Antonio Mallia and more

Potential Business Impact:

Shrinks computer memory for faster searching.

Business Areas:
Semantic Search Internet Services

High-dimensional dense embeddings have become central to modern Information Retrieval, but many dimensions are noisy or redundant. Recently proposed DIME (Dimension IMportance Estimation), provides query-dependent scores to identify informative components of embeddings. DIME relies on a costly grid search to select a priori a dimensionality for all the query corpus's embeddings. Our work provides a statistically grounded criterion that directly identifies the optimal set of dimensions for each query at inference time. Experiments confirm achieving parity of effectiveness and reduces embedding size by an average of $\sim50\%$ across different models and datasets at inference time.

Country of Origin
🇮🇹 Italy

Page Count
9 pages

Category
Computer Science:
Information Retrieval