The Everlasting Database: Statistical Validity at a Fair Price

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 $O(\sqrt{M})$.

22 pages, accepted to NeurIPS 2018

References in corpus (5)

• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Generalization in Adaptive Data Analysis and Holdout Reuse
• The Ladder: A Reliable Leaderboard for Machine Learning Competitions
• On the Generalization Properties of Differential Privacy
• Climbing a shaky ladder: Better adaptive risk estimation