ASM: Harmonizing Autoregressive Model, Sampling, and Multi-dimensional Statistics Merging for Cardinality Estimation

• DOI: 10.1145/3639300
• Publication Date: 2024-03-26T22:51:32Z
• Authors: Kyoungmin Kim; Sangoh Lee; Injung Kim; Wook-Shin Han
• Keywords: Cardinality (data modeling)

Recent efforts in learned cardinality estimation (CE) have substantially improved accuracy and query plans inside optimizers. However, achieving decent efficiency, scalability, the support of a wide range queries at same time, has remained questionable. Rather than falling back to traditional approaches trade off one criterion with another, we present new approach that achieves all these. Our method, called ASM, harmonizes autoregressive models for per-table statistics estimation, sampling merging these join queries, multi-dimensional extends estimating thousands sub-queries, without assuming independence between keys. Extensive experiments show ASM significantly improves under similar or smaller overhead previous methods supports wider queries.