Abstract
There are several interesting applications which are based on sequentially sampling individuals from an underlying population. Examples include online cardinality estimation [1-4] where the goal is to approximate the total size of the population and algorithms are typically based on the counting of 'collisions', i.e., instances where the sampled individual was 'seen' before; community exploration [5-7] where the goal is to discover as many distinct entities of interest as possible; and community detection / clustering [8-10] where the underlying population is naturally divided into communities / clusters and the goal is to estimate the true clustering using samples from the population.
Publisher
Association for Computing Machinery (ACM)
Reference15 articles.
1. Confidence intervals for the number of unseen types
2. Estimation of the number of operating sensors in large-scale sensor networks with mobile access
3. Marco Bressan, Enoch Peserico, and Luca Pretto. Simple set cardinality estimation through random sampling. arXiv preprint arXiv:1512.07901, 2015.
4. Peer counting and sampling in overlay networks
5. Xiaowei Chen, Weiran Huang, Wei Chen, and John CS Lui. Community exploration: from offline optimization to online learning. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018.