Mar 8, 2023 · We propose \textit{HappyMap}, a generalization of multi-calibration, which yields a wide range of new applications, including a new fairness notion for ...

Mar 8, 2023 · We propose HappyMap, a generalization of multicalibration, by enriching the class of mappings (alternatives for the term (f(x) − y) in Equation ...

Feb 1, 2023 · We propose s-Happy Multicalibration, a generalization of multi-calibration, which yields a wide range of new applications.

Duration: 19:20
Posted: Jan 5, 2023

Multi-calibration is a powerful and evolving concept originating in the field of algorithmic fairness. For a predictor $f$ that estimates the outcome $y$ ...

We show that such "loss-oblivious'' learning is feasible through a connection to multicalibration, a notion introduced in the context of algorithmic fairness.

Mar 8, 2023 · Multi-calibration is a powerful and evolving concept originating in the field of algorithmic fairness. For a predictor $f$ that estimates ...

Inproceedings, HappyMap : A Generalized Multicalibration Method. Z. Deng, C. Dwork, and L. Zhang. ITCS, volume 251 of LIPIcs, page 41:1-41:23.

This paper introduces a framework for post- processing machine learning models so that their predictions satisfy multi-group fairness guaran-.

HappyMap: A Generalized Multicalibration Method . ITCS 2023. Shirley Wu, Mert Yuksekgonul, Linjun Zhang and James Zou. (2023) Discover and Cure: Concept ...