High-dimensional similarity query processing for data science
Similarity query (aka nearest neighbor query) processing has been an active research topic
for several decades. It is an essential procedure in a wide range of applications (eg …
for several decades. It is an essential procedure in a wide range of applications (eg …
Deep non-crossing quantiles through the partial derivative
A Brando, BS Center… - International …, 2022 - proceedings.mlr.press
Quantile Regression (QR) provides a way to approximate a single conditional quantile. To
have a more informative description of the conditional distribution, QR can be merged with …
have a more informative description of the conditional distribution, QR can be merged with …
Cardinality estimation of approximate substring queries using deep learning
Cardinality estimation of an approximate substring query is an important problem in
database systems. Traditional approaches build a summary from the text data and estimate …
database systems. Traditional approaches build a summary from the text data and estimate …
Database optimizers in the era of learning
D Tsesmelis, A Simitsis - 2022 IEEE 38th International …, 2022 - ieeexplore.ieee.org
In this tutorial, we review advances made recently in a decades-old problem, namely query
optimization. Along with the traditional optimization techniques many of which are still being …
optimization. Along with the traditional optimization techniques many of which are still being …
[PDF][PDF] Similarity query processing for high-dimensional data
Similarity query processing has been an active research topic for several decades. It is an
essential procedure in a wide range of applications. Recently, embedding and auto …
essential procedure in a wide range of applications. Recently, embedding and auto …
Selectivity functions of range queries are learnable
This paper explores the use of machine learning for estimating the selectivity of range
queries in database systems. Using classic learning theory for real-valued functions based …
queries in database systems. Using classic learning theory for real-valued functions based …
HAP: an efficient hamming space index based on augmented pigeonhole principle
The emerging deep learning techniques prefer mapping complex data objects (eg, images,
documents) to compact binary vectors (ie, hash codes) for efficient similarity search. In this …
documents) to compact binary vectors (ie, hash codes) for efficient similarity search. In this …
Learned probing cardinality estimation for high-dimensional approximate NN search
Approximate nearest neighbor (ANN) search in high-dimensional space plays an essential
role in a variety of real-world applications. A well-known solution to ANN search, inverted file …
role in a variety of real-world applications. A well-known solution to ANN search, inverted file …
Learning-based query optimization for multi-probe approximate nearest neighbor search
Approximate nearest neighbor search (ANNS) is a fundamental problem that has attracted
widespread attention for decades. Multi-probe ANNS is one of the most important classes of …
widespread attention for decades. Multi-probe ANNS is one of the most important classes of …
Consistent and flexible selectivity estimation for high-dimensional data
Selectivity estimation aims at estimating the number of database objects that satisfy a
selection criterion. Answering this problem accurately and efficiently is essential to many …
selection criterion. Answering this problem accurately and efficiently is essential to many …