Research map / Architectures and efficiency / RNNs and normalization
Efficient Large-Scale Approximate Nearest Neighbor Search on the GPU
Check 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 the two-level Product Quantization Tree instead of IVFADC | ANN search · GIST1M | R@100: 0.744 -> 0.83 | Helped |
| Use the two-level Product Quantization Tree instead of IVFADC | ANN search · GIST1M | average query time (ms): 65.9 -> 63 | Hurt |
| Use PQT on GPU instead of FLANN on CPU | ANN search · SIFT1M | query time (ms): 5.32 -> 0.02 | Helped |
| Add exact re-ranking to PQT1 (ablation) | PQT1 (CPU) · SIFT1M | query time (ms): 4.89 -> 5.74 | Hurt |
| Increase line-quantization parts (ablation) | PQT · SIFT1M | recall | Helped |
| Increase line-quantization parts (ablation) | PQT · SIFT1M | query time (ms): 3, 4, 6, 9ms | Hurt |
| Use an anisotropic rather than naive isotropic bin traversal heuristic (ablation) | PQT · bin proposal | number of bins to reach ordering: 10 bins -> 8 bins | Helped |
Closest papers by meaning
- Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA (CVPR 2018 · similarity 0.90)
- Product Quantized Translation for Fast Nearest Neighbor Search (AAAI 2018 · similarity 0.88)
- LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search (NeurIPS 2024 · similarity 0.86)
- Approximate Nearest Neighbor Search with Window Filters (ICML 2024 · similarity 0.86)
- CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search (NeurIPS 2024 · similarity 0.84)
- LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing (NeurIPS 2024 · 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.