Paper Info
Title
A Comparative Study On Sampling With Replacement Vs Poisson Sampling In Optimal Subsampling
Abstract
Faced with massive data, subsampling is a commonly used technique to improve computational efficiency, and using nonuniform subsampling probabilities is an effective approach to improve estimation efficiency. For computational efficiency, subsampling is often implemented with replacement or through Poisson subsampling. However, no rigorous investigation has been performed to study the difference between the two subsampling procedures such as their estimation efficiency and computational convenience. In the context of maximizing a general target function, this paper derives optimal subsampling probabilities for both subsampling with replacement and Poisson subsampling. The optimal subsampling probabilities minimize variance functions of the subsampling estimators. Furthermore, they provide deep insights on the theoretical similarities and differences between subsampling with replacement and Poisson subsampling. Practically implementable algorithms are proposed based on the optimal structural results, which are evaluated by both theoretical and empirical analysis.
Year
Venue
DocType
2021
24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS)
Conference
Volume
ISSN
Citations 
130
2640-3498
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
haiying143.72
Jiahui Zou200.34