EUVIMEDEUVIMED entdecken
Crossref

Correcting Underrepresentation and Intersectional Bias in Machine Learning

Alexander Williams Tolbert

American Philosophical Quarterly · 01.04.2026 · 63 (2) · 183-199

DOI: 10.5406/21521123.63.2.07 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Philosophical Quarterly, online erschienen am 01.04.2026. Verfasst von Alexander Williams Tolbert. Die Arbeit nennt 6 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

I consider the problem of learning from data corrupted by underrepresentation bias, where positive examples are filtered out at different, unknown rates for a fixed number of sensitive groups. I show that with a small amount of unbiased data, I can efficiently estimate the group-wise drop-out rates, even in settings where intersectional group membership makes learning each intersectional rate computationally infeasible. Using these estimates, I construct a reweighting scheme that allows me to approximate the loss of any hypothesis on the true distribution and present an algorithm encapsulating this process. Finally, I define a bespoke notion of PAC learnability for the underrepresentation and intersectional bias setting and show that my algorithm allows efficient learning for model classes of finite VC dimension.

Zitieren

APA

Tolbert, A. W. (2026). Correcting Underrepresentation and Intersectional Bias in Machine Learning. American Philosophical Quarterly, 63(2), 183-199. https://doi.org/10.5406/21521123.63.2.07

Vancouver

Tolbert AW. Correcting Underrepresentation and Intersectional Bias in Machine Learning. American Philosophical Quarterly. 2026;63(2):183-199. doi:10.5406/21521123.63.2.07

BibTeX
@article{Tolbert2026,
  author = {Tolbert, Alexander Williams},
  title = {Correcting Underrepresentation and Intersectional Bias in Machine Learning},
  journal = {American Philosophical Quarterly},
  year = {2026},
  volume = {63},
  number = {2},
  pages = {183--199},
  doi = {10.5406/21521123.63.2.07}
}
Kostenlos starten →