RadixSpline: A Single-Pass Learned Index

TL;DR

RadixSpline is a novel learned index structure that can be built in a single pass, offering competitive size and lookup performance compared to existing models like RMI, simplifying implementation and construction.

Contribution

Introduces RadixSpline, a single-pass learned index structure that is easy to implement and maintains competitive performance with state-of-the-art models.

Findings

RadixSpline achieves comparable size and lookup speed to RMI.

It requires only two parameters, simplifying tuning.

Performance is validated on the SOSD benchmark across multiple datasets.

Abstract

Recent research has shown that learned models can outperform state-of-the-art index structures in size and lookup performance. While this is a very promising result, existing learned structures are often cumbersome to implement and are slow to build. In fact, most approaches that we are aware of require multiple training passes over the data. We introduce RadixSpline (RS), a learned index that can be built in a single pass over the data and is competitive with state-of-the-art learned index models, like RMI, in size and lookup performance. We evaluate RS using the SOSD benchmark and show that it achieves competitive results on all datasets, despite the fact that it only has two parameters.