Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
Grid-based multiprobe algorithms demonstrate superior dimensional scaling properties compared to graph-, tree-, and partitioning-based methods for approximate nearest neighbor sear…
Hugging Face · Daily Papers
·Matthew J Liu, Wei Hang Zheng
·
·▲ 2 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Matthew J Liu, Wei Hang Zheng, Vidhan Purohit, Siqi Xie, Chieh-En Li, Jerry Li
- 2 upvotes da comunidade
- Temas: approximate nearest neighbor search, multiprobe grid algorithm, dataset size, dimensionality, GloVe embedding, indexing cost
Resumo
Resumo original (em inglês), extraído do paper:
Grid-based multiprobe algorithms demonstrate superior dimensional scaling properties compared to graph-, tree-, and partitioning-based methods for approximate nearest neighbor search, making them competitive for high-dimensional and rebuild-heavy applications.