NeurIPS 2018poster30 citations
Data Amplification: A Unified and Competitive Approach to Property Estimation
Yi Hao, Alon Orlitsky, Ananda Theertha Suresh, Yihong Wu
Abstract
Estimating properties of discrete distributions is a fundamental problem in statistical learning. We design the first unified, linear-time, competitive, property estimator that for a wide class of properties and for all underlying distributions uses just 2n samples to achieve the performance attained by the empirical estimator with n\sqrt{\log n} samples. This provides off-the-shelf, distribution-independent, ``amplification'' of the amount of data available relative to common-practice estimators.
BibTeX
@inproceedings{NEURIPS2018_a753a435,
author = {Hao, Yi and Orlitsky, Alon and Suresh, Ananda Theertha and Wu, Yihong},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Data Amplification: A Unified and Competitive Approach to Property Estimation},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/a753a43564c29148df3150afb4475440-Paper.pdf},
volume = {31},
year = {2018}
}