Research map / Architectures and efficiency / RNNs and normalization
Fast Partitioned Learned Bloom Filter
Atsuki Sato, Yusuke Matsui
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use DP-table reuse (fast PLBF) instead of PLBF | PLBF · URLs | construction time: 50.8 times faster | Improved |
| use DP-table reuse (fast PLBF) instead of PLBF | PLBF · EMBER | construction time: 34.3 times faster | Improved |
| use monotone-matrix KL-divergence DP (fast PLBF++) instead of PLBF | PLBF · URLs | construction time: 63.1 times faster | Improved |
| use fast PLBF++ instead of PLBF | PLBF · EMBER | construction time: 39.3 times faster | Improved |
| use fast PLBF++ instead of PLBF | PLBF · URLs | false positive rate: up to 1.0019 times higher | No clear effect |
| use fast PLBF++ instead of PLBF | PLBF · EMBER | false positive rate: up to 1.000083 times higher | No clear effect |
| use fast PLBF instead of PLBF | PLBF · URLs and EMBER | false positive rate | No clear effect |
| increase N (ablation) | PLBF, fast PLBF, fast PLBF++ · URLs and EMBER | test false positive rate | Improved |
| increase N (ablation) | fast PLBF++ · URLs and EMBER | construction time | No clear effect |
| increase k (ablation) | PLBF, fast PLBF, fast PLBF++ · EMBER | false positive rate: stops decreasing at about k=20 | Mixed |
| increase k (ablation) | PLBF, fast PLBF, fast PLBF++ · URLs | false positive rate: continues to decrease even at about k=500 | Improved |
| use fast PLBF vs PLBF at k=50 (ablation) | PLBF · URLs | construction time: 233 times faster | Improved |
Closest papers by meaning
- Ensemble Learned Bloom Filters: Two Oracles are Better than One (ICML 2025 · similarity 0.90)
- LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table (CVPR 2025 · similarity 0.82)
- FlashBias: Fast Computation of Attention with Bias (NeurIPS 2025 · similarity 0.81)
- SlimSAM: 0.1% Data Makes Segment Anything Slim (NeurIPS 2024 · similarity 0.81)
- Learning-Augmented Search Data Structures (ICLR 2025 · similarity 0.81)
- Discovering Data Structures: Nearest Neighbor Search and Beyond (NeurIPS 2025 · similarity 0.81)
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.
