HappyMap: A Generalized Multicalibration Method

Zhun Deng, Cynthia Dwork, Linjun Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Scopus citations

Abstract

Multicalibration is a powerful and evolving concept originating in the field of algorithmic fairness. For a predictor f that estimates the outcome y given covariates x, and for a function class C, multi-calibration requires that the predictor f(x) and outcome y are indistinguishable under the class of auditors in C. Fairness is captured by incorporating demographic subgroups into the class of functions C. Recent work has shown that, by enriching the class C to incorporate appropriate propensity re-weighting functions, multi-calibration also yields target-independent learning, wherein a model trained on a source domain performs well on unseen, future, target domains (approximately) captured by the re-weightings. Formally, multicalibration with respect to C bounds E(x,y)∼D[c(f(x), x) · (f(x) − y)] for all c ∈ C. In this work, we view the term (f(x) − y) as just one specific mapping, and explore the power of an enriched class of mappings. We propose s-Happy Multicalibration, a generalization of multi-calibration, which yields a wide range of new applications, including a new fairness notion for uncertainty quantification, a novel technique for conformal prediction under covariate shift, and a different approach to analyzing missing data, while also yielding a unified understanding of several existing seemingly disparate algorithmic fairness notions and target-independent learning approaches. We give a single HappyMap meta-algorithm that captures all these results, together with a sufficiency condition for its success.

Original languageEnglish (US)
Title of host publication14th Innovations in Theoretical Computer Science Conference, ITCS 2023
EditorsYael Tauman Kalai
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
ISBN (Electronic)9783959772631
DOIs
StatePublished - Jan 1 2023
Event14th Innovations in Theoretical Computer Science Conference, ITCS 2023 - Cambridge, United States
Duration: Jan 10 2023Jan 13 2023

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume251
ISSN (Print)1868-8969

Conference

Conference14th Innovations in Theoretical Computer Science Conference, ITCS 2023
Country/TerritoryUnited States
CityCambridge
Period1/10/231/13/23

All Science Journal Classification (ASJC) codes

  • Software

Keywords

  • algorithmic fairness
  • target-independent learning
  • transfer learning

Fingerprint

Dive into the research topics of 'HappyMap: A Generalized Multicalibration Method'. Together they form a unique fingerprint.

Cite this