The privacy-fairness tension is considerably weaker than previously believed. It appears largely to be an artifact of algorithm design.
🌐 https://t.co/w632kACccA
📄 https://t.co/H3hPUzEfB7
💻 https://t.co/HMoTigYvWI
Can ML models be trained under fairness constraints with formal DP guarantees, without sacrificing utility?
New paper at ICLR 2026: RaCO-DP
Poster: Pavilion 4 (later today!)
🧵
(w/ @tudorcebere, Michael Menart, Aurélien Bellet, @NicolasPapernot )
Unlike regularization-based methods, RaCO-DP enforces bounds directly by construction: no hyperparameter tuning, no extra privacy cost.
Also scales to many simultaneous constraints without degradation, and runs three orders of magnitude faster than the prior SOTA, DP-FERMI.
Curious about novel risks that AI introduces for patients and healthcare providers?
We're hosting an #AIUK Fringe event to explore Privacy and Fairness in AI for Health – Register now!
https://t.co/oUSY5wgqsC
Date: 27 March, 10:00-16:30 GMT
Location: @turinginst, London
1/6
@hiddenmarkov@Aaroth Moreover, we show, via a probabilistic formulation, how the main cause of disparity is two-fold: under/over representation and model generalization differences across subgroups.