Skip to yearly menu bar Skip to main content


Poster

The Everlasting Database: Statistical Validity at a Fair Price

Blake Woodworth · Vitaly Feldman · Saharon Rosset · Nati Srebro

Room 517 AB #103

Keywords: [ Learning Theory ] [ Computational Social Science ] [ Adaptive Data Analysis ]


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 $O(\sqrt{M})$.

Live content is unavailable. Log in and register to view live content