paper-with-me

Papers

The Everlasting Database: Statistical Validity at a Fair Price

2018-03-12 · NeurIPS 2018 12 · Blake Woodworth, Vitaly Feldman, Saharon Rosset, Nathan Srebro

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 $O(\sqrt{M})$.

📄 PDF Abstract BibTeX arXiv:1803.04307

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Clearing price distributions in call auctions

2019-04-16 · M. Derksen, B. Kleijn, R. de Vilder

We propose a model for price formation in financial markets based on clearing of a standard call auction with random orders, and verify its validity for prediction of the daily closing price distribution statistically. T…

Private Truly-Everlasting Robust-Prediction

2024-01-09 · Uri Stemmer

Private Everlasting Prediction (PEP), recently introduced by Naor et al. [2023], is a model for differentially private learning in which the learner never publicly releases a hypothesis. Instead, it provides black-box ac…

Prediction

Capuchin: Causal Database Repair for Algorithmic Fairness

2019-02-21 · Babak Salimi, Luke Rodriguez, Bill Howe, Dan Suciu

Fairness is increasingly recognized as a critical component of machine learning systems. However, it is the underlying data on which these systems are trained that often reflect discrimination, suggesting a database repa…

Fairness

A Discussion of Discrimination and Fairness in Insurance Pricing

2022-09-02 · Mathias Lindholm, Ronald Richman, Andreas Tsanakas, Mario V. Wüthrich

Indirect discrimination is an issue of major concern in algorithmic models. This is particularly the case in insurance pricing where protected policyholder characteristics are not allowed to be used for insurance pricing…

Fairness

Review of Mathematical frameworks for Fairness in Machine Learning

2020-05-26 · Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes

A review of the main fairness definitions and fair learning methodologies proposed in the literature over the last years is presented from a mathematical point of view. Following our independence-based approach, we consi…

BIG-bench Machine LearningFairnessregression