Deep Unsupervised Cardinality Estimation
This work addresses the challenge of accurate and efficient cardinality estimation in database systems, which is crucial for query optimization, but it is incremental as it builds on deep learning techniques applied to a known bottleneck.
The paper tackled the problem of cardinality estimation for relational tables by proposing a deep autoregressive model with a Monte Carlo integration scheme to handle range queries efficiently, achieving up to 90x accuracy improvement and single-digit multiplicative error at tail compared to existing methods.
Cardinality estimation has long been grounded in statistical tools for density estimation. To capture the rich multivariate distributions of relational tables, we propose the use of a new type of high-capacity statistical model: deep autoregressive models. However, direct application of these models leads to a limited estimator that is prohibitively expensive to evaluate for range or wildcard predicates. To produce a truly usable estimator, we develop a Monte Carlo integration scheme on top of autoregressive models that can efficiently handle range queries with dozens of dimensions or more. Like classical synopses, our estimator summarizes the data without supervision. Unlike previous solutions, we approximate the joint data distribution without any independence assumptions. Evaluated on real-world datasets and compared against real systems and dominant families of techniques, our estimator achieves single-digit multiplicative error at tail, an up to 90$\times$ accuracy improvement over the second best method, and is space- and runtime-efficient.