2026-07-21T23:56:38Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:23134 2025-10-02T12:34:53Z ddc:004 open_access

Kernel Multiaccuracy Long, Carol Xuan Alghamdi, Wael Glynn, Alexander Wu, Yixuan Calmon, Flavio P. algorithmic fairness integral probability metrics information theory Predefined demographic groups often overlook the subpopulations most impacted by model errors, leading to a growing emphasis on data-driven methods that pinpoint where models underperform. The emerging field of multi-group fairness addresses this by ensuring models perform well across a wide range of group-defining functions, rather than relying on fixed demographic categories. We demonstrate that recently introduced notions of multi-group fairness can be equivalently formulated as integral probability metrics (IPM). IPMs are the common information-theoretic tool that underlie definitions such as multiaccuracy, multicalibration, and outcome indistinguishably. For multiaccuracy, this connection leads to a simple, yet powerful procedure for achieving multiaccuracy with respect to an infinite-dimensional class of functions defined by a reproducing kernel Hilbert space (RKHS): first perform a kernel regression of a model’s errors, then subtract the resulting function from a model’s predictions. We combine these results to develop a post-processing method that improves multiaccuracy with respect to bounded-norm functions in an RKHS, enjoys provable performance guarantees, and, in binary classification benchmarks, achieves favorable multiaccuracy relative to competing methods. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Carol Xuan Long and Wael Alghamdi and Alexander Glynn and Yixuan Wu and Flavio P. Calmon 2025 Is Part Of LIPIcs, Volume 329, 6th Symposium on Foundations of Responsible Computing (FORC 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.FORC.2025.7 urn:nbn:de:0030-drops-231341 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2025.7 eng https://creativecommons.org/licenses/by/4.0/legalcode