AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

The Everlasting Database: Statistical Validity at a Fair Price

Blake E Woodworth, Vitaly Feldman, Saharon Rosset, Nati Srebro

NeurIPS 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Charge per query and use the revenue to purchase additional samples across roundsEverlastingValidation · Arbitrary adaptive statistical queriesanswer accuracy: 1 - \frac{\beta}{2}Improved
Use a decreasing low price for queries and charge a high price when a query prematurely ends a roundEverlastingValidation · M non-adaptive queriestotal cost: \frac{96}{\tau^2}\parens{1 + \ln(M)}Improved
Use ValidationRound with truncated Gaussian noise and a check comparing empirical means on two datasetsEverlastingValidation · M autonomous adaptive queriestotal cost: 1890\sqrt{M}\ln^2\parens{16M^2/\beta}/\tau^2Improved
Replace ValidationRound with Thresholdout and tune the tradeoff parameter pEverlastingTO · Non-adaptive and potentially adaptive queriestotal cost: O\parens{\ln^{1/p}(M) + B^{\frac{1}{2-3p}}}Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy