paper-with-me

Papers

An Exploration of Multicalibration Uniform Convergence Bounds

2022-02-09 · Harrison Rosenberg, Robi Bhattacharjee, Kassem Fawaz, Somesh Jha

Recent works have investigated the sample complexity necessary for fair machine learning. The most advanced of such sample complexity bounds are developed by analyzing multicalibration uniform convergence for a given predictor class. We present a framework which yields multicalibration error uniform convergence bounds by reparametrizing sample complexities for Empirical Risk Minimization (ERM) learning. From this framework, we demonstrate that multicalibration error exhibits dependence on the classifier architecture as well as the underlying data distribution. We perform an experimental evaluation to investigate the behavior of multicalibration error for different families of classifiers. We compare the results of this evaluation to multicalibration error concentration bounds. Our investigation provides additional perspective on both algorithmic fairness and multicalibration error convergence bounds. Given the prevalence of ERM sample complexity bounds, our proposed framework enables machine learning practitioners to easily understand the convergence behavior of multicalibration error for a myriad of classifier architectures.

📄 PDF Abstract BibTeX arXiv:2202.04530

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningFairness

Similar Papers 제목 키워드 기반

Sample Complexity of Uniform Convergence for Multicalibration

2020-05-04 · NeurIPS 2020 12 · Eliran Shabat, Lee Cohen, Yishay Mansour

There is a growing interest in societal concerns in machine learning systems, especially in fairness. Multicalibration gives a comprehensive methodology to address group fairness. In this work, we address the multicalibr…

Fairness

Optimal Lower Bounds for Online Multicalibration

2026-01-08 · Natalie Collina, Jiuyao Lu, Georgy Noarov, Aaron Roth arxiv

We prove tight lower bounds for online multicalibration, establishing an information-theoretic separation from marginal calibration. In the general setting where group functions can depend on both context and the learner…

On the Convergence of Multicalibration Gradient Boosting

2026-02-06 · Daniel Haimovich, Fridolin Linder, Lorenzo Perini, Niek Tax 외 arxiv

Multicalibration gradient boosting has recently emerged as a scalable method that empirically produces approximately multicalibrated predictors and has been deployed at web scale. Despite this empirical success, its conv…

The Sample Complexity of Multicalibration

2026-04-23 · Natalie Collina, Jiuyao Lu, Georgy Noarov, Aaron Roth arxiv

We study the minimax sample complexity of multicalibration in the batch setting. A learner observes $n$ i.i.d. samples from an unknown distribution and must output a (possibly randomized) predictor whose population multi…

Multicalibration as Boosting for Regression

2023-01-31 · Ira Globus-Harris, Declan Harrison, Michael Kearns, Aaron Roth 외

We study the connection between multicalibration and boosting for squared error regression. First we prove a useful characterization of multicalibration in terms of a ``swap regret'' like condition on squared error. Usin…

regression