The Everlasting Database: Statistical Validity at a Fair Price
Blake E Woodworth, Vitaly Feldman, Saharon Rosset, Nati Srebro
Abstract
The problem of handling adaptivity in data analysis, intentional or not, permeates a variety of fields, including test-set overfitting in ML challenges and the accumulation of invalid scientific discoveries. We propose a mechanism for answering an arbitrarily long sequence of potentially adaptive statistical queries, by charging a price for each query and using the proceeds to collect additional samples. Crucially, we guarantee statistical validity without any assumptions on how the queries are generated. We also ensure with high probability that the cost for $M$ non-adaptive queries is $O(\log M)$, while the cost to a potentially adaptive user who makes $M$ queries that do not depend on any others is $O(\sqrt{M})$.
BibTeX
@inproceedings{NEURIPS2018_4ad13f04,
author = {Woodworth, Blake E and Feldman, Vitaly and Rosset, Saharon and Srebro, Nati},
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 = {The Everlasting Database: Statistical Validity at a Fair Price},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/4ad13f04ef4373992c9d3046200aa350-Paper.pdf},
volume = {31},
year = {2018}
}