Research map / Learning theory and algorithms / Prediction and decision losses
A Model for Learned Bloom Filters and Optimizing by Sandwiching
Michael Mitzenmacher
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 |
|---|---|---|---|
| Add an initial Bloom filter before the learned function and backup filter (ablation) | Learned Bloom filter · Sandwiched example, b = 8 bits per key | false positive rate: approximately 0.010045 -> 0.005012 | Improved |
| Add an initial Bloom filter before the learned function and backup filter (ablation) | Learned Bloom filter · Sandwiched example, b = 10 bits per key | false positive rate: 0.010066 -> 0.001917 | Improved |
| Use queries uniform over [0,100000) rather than [0,1000000) | Learned Bloom filter · Illustrative query-distribution example | false positive rate: 0.0004 -> 0.0022 | Hurt |
| Use a learned function with 3 bits per item and a backup filter holding the false negatives | Standard Bloom filter · Modeled example, 1 byte per item | false positive rate: approximately 0.0214 -> approximately 0.0181 | Improved |
Closest papers by meaning
- Ensemble Learned Bloom Filters: Two Oracles are Better than One (ICML 2025 · similarity 0.91)
- A Bitter Lesson for Data Filtering (NeurIPS 2026 · similarity 0.84)
- Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic (CVPR 2024 · similarity 0.82)
- Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability (ICML 2024 · similarity 0.82)
- TFG: Unified Training-Free Guidance for Diffusion Models (NeurIPS 2024 · similarity 0.82)
- Data Filtering Networks (ICLR 2024 · 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.
