Towards Practical Learned Indexing [article]

Mihail Stoian and Andreas Kipf and Ryan Marcus and Tim Kraska
2021 arXiv   pre-print
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)
more » ... dix 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.
arXiv:2108.05117v2 fatcat:jde3h4irbvhbfpra7qrzrhxqmm