Timezone: »

 
Poster
The Everlasting Database: Statistical Validity at a Fair Price
Blake Woodworth · Vitaly Feldman · Saharon Rosset · Nati Srebro

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #103
in Wed Poster Session B »
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 $O(\sqrt{M})$.
Keywords: Learning Theory · Computational Social Science · Adaptive Data Analysis
[ Paper] 

Author Information

Blake Woodworth (TTI-Chicago)
Vitaly Feldman (Google Brain)
Saharon Rosset (Technion)
Nati Srebro (TTI-Chicago)

More from the Same Authors