Automating Nearest Neighbor Search Configuration with Constrained Optimization

TL;DR

This paper introduces an automated method for tuning parameters in approximate nearest neighbor search algorithms using constrained optimization, improving ease of use and performance.

Contribution

It presents a novel constrained optimization approach that automates parameter tuning for ANN algorithms based on desired speed or recall, reducing manual effort.

Findings

Achieves near Pareto-optimal speed-recall tradeoffs

Outperforms manually tuned configurations on benchmarks

Simplifies deployment of ANN search in real-world applications

Abstract

The approximate nearest neighbor (ANN) search problem is fundamental to efficiently serving many real-world machine learning applications. A number of techniques have been developed for ANN search that are efficient, accurate, and scalable. However, such techniques typically have a number of parameters that affect the speed-recall tradeoff, and exhibit poor performance when such parameters aren't properly set. Tuning these parameters has traditionally been a manual process, demanding in-depth knowledge of the underlying search algorithm. This is becoming an increasingly unrealistic demand as ANN search grows in popularity. To tackle this obstacle to ANN adoption, this work proposes a constrained optimization-based approach to tuning quantization-based ANN algorithms. Our technique takes just a desired search cost or recall as input, and then generates tunings that, empirically, are very close to the speed-recall Pareto frontier and give leading performance on standard benchmarks.