Indistinguishable predictions and multi-group fair learning

DOI10.1007/978-3-031-30545-0_1MaRDI QIDQ6138076zbMATH OpenOpenAlexFDO

Authors Guy N. Rothblum

Publication date 16 January 2024

Published in Advances in Cryptology – EUROCRYPT 2023 (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-031-30545-0_1

zbMATH Keywords

computational indistinguishabilityprediction algorithmsoutcome indistinguishability

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Outcome indistinguishability
• Fairness through awareness
• Fairness under composition
• Inherent tradeoffs in learning fair representations
• Achieving fair treatment in algorithmic classification

Cites work

• scientific article; zbMATH DE number 5081837 (Why is no real title available?)
• scientific article; zbMATH DE number 6866333 (Why is no real title available?)
• scientific article; zbMATH DE number 7489400 (Why is no real title available?)
• Advancing subgroup fairness via sleeping experts
• An easier way to calibrate.
• Asymptotic calibration
• Calibration with Many Checking Rules
• Can theories be tested?
• Computational Complexity
• Fairness through awareness
• Foundations of Cryptography
• On individual risk
• Outcome indistinguishability
• Pseudorandomness
• The Complexity of Forecast Testing
• The Well-Calibrated Bayesian
• The reproducible properties of correct forecasts
• Toward efficient agnostic learning

Cited in

(1)

• Outcome indistinguishability

This page was built for publication: Indistinguishable predictions and multi-group fair learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138076)