AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Fast Partitioned Learned Bloom Filter

Atsuki Sato, Yusuke Matsui

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Distributed LLM inference systems · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use DP-table reuse (fast PLBF) instead of PLBFPLBF · URLsconstruction time: 50.8 times fasterImproved
use DP-table reuse (fast PLBF) instead of PLBFPLBF · EMBERconstruction time: 34.3 times fasterImproved
use monotone-matrix KL-divergence DP (fast PLBF++) instead of PLBFPLBF · URLsconstruction time: 63.1 times fasterImproved
use fast PLBF++ instead of PLBFPLBF · EMBERconstruction time: 39.3 times fasterImproved
use fast PLBF++ instead of PLBFPLBF · URLsfalse positive rate: up to 1.0019 times higherNo clear effect
use fast PLBF++ instead of PLBFPLBF · EMBERfalse positive rate: up to 1.000083 times higherNo clear effect
use fast PLBF instead of PLBFPLBF · URLs and EMBERfalse positive rateNo clear effect
increase N (ablation)PLBF, fast PLBF, fast PLBF++ · URLs and EMBERtest false positive rateImproved
increase N (ablation)fast PLBF++ · URLs and EMBERconstruction timeNo clear effect
increase k (ablation)PLBF, fast PLBF, fast PLBF++ · EMBERfalse positive rate: stops decreasing at about k=20Mixed
increase k (ablation)PLBF, fast PLBF, fast PLBF++ · URLsfalse positive rate: continues to decrease even at about k=500Improved
use fast PLBF vs PLBF at k=50 (ablation)PLBF · URLsconstruction time: 233 times fasterImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy