Towards Practical Learned Indexing

by   Mihail Stoian, et al.

Latest research proposes to replace existing index structures with learned models. However, current learned indexes tend to have many hyperparameters, often do not provide any error guarantees, and are expensive to build. We introduce Practical Learned Index (PLEX). PLEX only has a single hyperparameter ϵ (maximum prediction error) and offers a better trade-off between build and lookup time than state-of-the-art approaches. Similar to RadixSpline, PLEX consists of a spline and a (multi-level) radix layer. It first builds a spline satisfying the given ϵ and then performs an ad-hoc analysis of the distribution of spline points to quickly tune the radix layer.


page 1

page 2

page 3

page 4


RadixSpline: A Single-Pass Learned Index

Recent research has shown that learned models can outperform state-of-th...

Benchmarking Learned Indexes

Recent advancements in learned index structures propose replacing existi...

Spline Based Intrusion Detection in Vehicular Ad Hoc Networks (VANET)

Intrusion detection systems (IDSs) play a crucial role in the identifica...

A Critical Analysis of Recursive Model Indexes

The recursive model index (RMI) has recently been introduced as a machin...

Error analysis for local coarsening in univariate spline spaces

In this article we analyze the error produced by the removal of an arbit...

NFL: Robust Learned Index via Distribution Transformation

Recent works on learned index open a new direction for the indexing fiel...

Tune: A Research Platform for Distributed Model Selection and Training

Modern machine learning algorithms are increasingly computationally dema...

Please sign up or login with your details

Forgot password? Click here to reset