… estimates in the first place, we demonstrate that the estimates produced by Deep Sketches
are superior to estimates of traditional optimizers and often close to the ground truth. The …

… As already demonstrated by [11, 14, 16], the application of deep learning techniques to
the cardinality estimation task enhances the accuracy compared to traditional approaches. …

… We compare to a recently proposed supervised deep net-based estimator termed multi-set
convolutional network [22], or MSCN. We apply the source code from the authors [21] to our …

… and evaluate deep learning for cardinality estimation by … We find that simple deep learning
models can learn cardinality … of injecting cardinality estimates produced by deep learning …

… We will delve deeper into this intuition and formalize it in the subsequent sections. Crucially,
… 5 iid estimates as the cardinality estimate for all sketching methods. 4.2 Estimation accuracy …

… , sketch usage for cardinality estimation in query optimization is limited. Following recent work
that applies transformers to cardinality estimation… Moving away from deep learning models …

… estimation challenge [16]. Our approach builds on sampling-based estimation by including
cardinalities … Most sampling proposals create per-table samples/sketches and try to combine …

… cardinality estimation. Traditional data-driven methods include data-driven histograms,
sampling, and sketching. … -driven cardinality estimation by formulating cardinality estimation as a …

… estimates in the first place, we demonstrate that the estimates produced by Deep Sketches
are superior to estimates of traditional optimizers and often close to the ground truth. The …

… possibilities of utilizing deep learning for cardinality estimation of similarity selection. …
estimated cardinality is supposed to be consistent and interpretable. Hence a monotonic estimation …