Research map / Learning theory and algorithms / Prediction and decision losses
Norm-Ranging LSH for Maximum Inner Product Search
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 |
|---|---|---|---|
| partition items by 2-norm percentiles and normalize each sub-dataset by its local maximum norm | SIMPLE-LSH, producing NORM-RANGING LSH · Netflix | probed items at fixed recall | Helped |
| partition items by 2-norm percentiles and normalize each sub-dataset by its local maximum norm | SIMPLE-LSH, producing NORM-RANGING LSH · Yahoo!Music | probed items at fixed recall | Helped |
| partition items by 2-norm percentiles and normalize each sub-dataset by its local maximum norm | SIMPLE-LSH, producing NORM-RANGING LSH · ImageNet | probed items at fixed recall | Helped |
| use uniform norm-range partitioning instead of percentile partitioning (ablation) | NORM-RANGING LSH · Yahoo!Music | probed items at fixed recall | Helped |
| increase the number of sub-datasets while it is still small (ablation) | NORM-RANGING LSH · Yahoo!Music | probed items at fixed recall | Helped |
| increase the number of sub-datasets after it is sufficiently large (ablation) | NORM-RANGING LSH · Yahoo!Music | probed items at fixed recall | No clear effect |
| partition the dataset into norm-similar sub-datasets and use local normalization | L2-ALSH · MIPS | query time complexity | Helped |
Closest papers by meaning
- SAH: Shifting-Aware Asymmetric Hashing for Reverse k Maximum Inner Product Search (AAAI 2023 · similarity 0.87)
- Query-Aware Quantization for Maximum Inner Product Search (AAAI 2023 · similarity 0.86)
- Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search (NeurIPS 2023 · similarity 0.85)
- Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search (NeurIPS 2025 · similarity 0.85)
- Understanding and Improving Proximity Graph Based Maximum Inner Product Search (AAAI 2020 · similarity 0.85)
- Faster Maximum Inner Product Search in High Dimensions (ICML 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.