Research map / Learning theory and algorithms / Prediction and decision losses
Practical Near Neighbor Search via Group Testing
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FLINNG instead of FAISS | YFCC100M search at 0.99 recall · YFCC100M | query speed: 3.4 times faster | Helped |
| Use FLINNG instead of HNSW | PromethION search at 0.8 recall · PromethION | query speed: 4x faster | Helped |
| Use FLINNG instead of FAISS | YFCC100M index construction · YFCC100M | indexing time: 40 sec vs 12 hr | Helped |
| Use FLINNG instead of HNSW | YFCC100M index construction · YFCC100M | memory: 3.5 GB vs >1 TB | Helped |
| Use FLINNG instead of FLASH | YFCC100M index construction · YFCC100M | indexing time: 40 sec vs 80 sec | Helped |
Closest papers by meaning
- Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search (NeurIPS 2022 · similarity 0.90)
- Graph-Based Algorithms for Diverse Similarity Search (ICML 2025 · similarity 0.86)
- Fast k-Nearest Neighbour Search via Dynamic Continuous Indexing (ICML 2016 · similarity 0.86)
- Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search (NeurIPS 2025 · similarity 0.85)
- Efficient Centroid-Linkage Clustering (NeurIPS 2024 · similarity 0.85)
- Searching for and Avoiding Hidden Sets Using Queries with Local Feedback (AAAI 2025 · similarity 0.84)
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.