@inproceedings{d-erasmo-etal-2026-statistical,
    title = "Statistical Foundations of {DIME}: Risk Estimation for Practical Index Selection",
    author = "D'Erasmo, Giulio  and
      Campagnano, Cesare  and
      Mallia, Antonio  and
      Brutti, Pierpaolo  and
      Tonellotto, Nicola  and
      Silvestri, Fabrizio",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-short.51/",
    pages = "722--730",
    ISBN = "979-8-89176-381-4",
    abstract = "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 that this approach improves retrieval effectiveness and reduces embedding size by an average 50{\%} of across different models and datasets at inference time."
}