Cardinality estimation with smoothing autoregressive models

Cardinality estimation, which aims at accurately estimating the result size of queries, is a fundamental task in database query processing and optimization. One of the most recent and effective solutions to this problem is the use of deep autoregressive models to obtain joint probability distributions through unsupervised learning. However, due to the data sparsity, it is difficult for the estimator to accurately capture the actual distribution, which affects the accuracy of the cardinality estimation. In addition, autoregressive estimators' progressive sampling characteristics are prone to error propagation, which is more evident in high-dimensional data. To reduce the autoregressive cardinality estimation error and to obtain a better trade-off between estimate accuracy and latency, we propose a random smoothing autoregressive cardinality estimation model (SAM-CE), which uses a random smoothing technique combined with a deep autoregressive model to simplify the learning of joint probability distributions. A smooth progressive sampling method that is suitable for range queries is designed to improve the estimator accuracy by improving the sample quality. We conduct extensive experiments to demonstrate the effectiveness and performance of the proposed SAM-CE. The results show that SAM-CE achieves the state of the art effectiveness of cardinality estimation.