Summary of Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search, by Sebastian Bruch et al.
Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
by Sebastian Bruch, Aditya Krishnan, Franco Maria Nardini
First submitted to arxiv on: 20 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed framework for clustering-based maximum inner product search improves routing efficacy by formalizing the concept of “optimism in the face of uncertainty.” This approach incorporates moments of the distribution of inner products within each shard to estimate the maximum inner product. The presented algorithm achieves state-of-the-art accuracy with up to 50% fewer probes on benchmark datasets, while also being space-efficient. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Clustering-based nearest neighbor search is a method that groups points into geometric shards for efficient query processing. While it’s effective, the algorithm used to identify which shards to probe has been largely overlooked in research. This paper explores routing in clustering-based maximum inner product search and finds that incorporating optimism can improve results. The proposed framework uses moments of the distribution of inner products within each shard to estimate the maximum inner product, achieving similar accuracy with fewer probes. |
Keywords
» Artificial intelligence » Clustering » Nearest neighbor
