The Everlasting Database: Statistical Validity at a Fair Price

2018/03/12 by Blake Woodworth, Woodworth, Blake, Vitaly Feldman +5
Computer Science · #Advanced Data Storage Technologies #Algorithms and Data Compression #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.1803.04307

openalex publication_date 2018/03/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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(√(M)).

Citations

• The Ladder: A Reliable Leaderboard for Machine Learning Competitions
• Observation of a new particle in the search for the Standard Model Higgs boson with the ATLAS detector at the LHC
• Calibrating Noise to Sensitivity in Private Data Analysis
• On the Generalization Properties of Differential Privacy
• The Statistical Crisis in Science
• Climbing a shaky ladder: Better adaptive risk estimation

Related

• Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis
• Sampling Without Compromising Accuracy in Adaptive Data Analysis
• Algorithmic Stability for Adaptive Data Analysis
• Preventing False Discovery in Interactive Data Analysis is Hard
• A Minimax Theory for Adaptive Data Analysis