@inproceedings{4098f36a93fd4b569b2f30b05ad3e695,
title = "Affirmative Sampling: Theory and Applications",
abstract = "Affirmative Sampling is a practical and efficient novel algorithm to obtain random samples of distinct elements from a data stream. Its most salient feature is that the size S of the sample will, on expectation, grow with the (unknown) number n of distinct elements in the data stream. As any distinct element has the same probability to be sampled, and the sample size is greater when the “diversity” (the number of distinct elements) is greater, the samples that Affirmative Sampling delivers are more representative than those produced by any scheme where the sample size is fixed a priori - hence its name. Our algorithm is straightforward to implement, and several implementations already exist.",
keywords = "Analysis of algorithms, Cardinality estimation, Data streams, Distinct sampling, Random sampling",
author = "J{\'e}r{\'e}mie Lumbroso and Conrado Mart{\'i}nez",
note = "Publisher Copyright: {\textcopyright} J{\'e}r{\'e}mie Lumbroso and Conrado Mart{\'i}nez; licensed under Creative Commons License CC-BY 4.0; 33rd International Conference on Probabilistic, Combinatorial and Asymptotic Methods for the Analysis of Algorithms, AofA 2022 ; Conference date: 20-06-2022 Through 24-06-2022",
year = "2022",
month = jun,
day = "1",
doi = "10.4230/LIPIcs.AofA.2022.12",
language = "English (US)",
series = "Leibniz International Proceedings in Informatics, LIPIcs",
publisher = "Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing",
editor = "Ward, {Mark Daniel}",
booktitle = "33rd International Conference on Probabilistic, Combinatorial and Asymptotic Methods for the Analysis of Algorithms, AofA 2022",
address = "Germany",
}