RaCO-DP is a differentially private SGDA algorithm that enforces arbitrary prediction-rate constraints, such as group fairness and false negative rate limits, using a private histogram per mini-batch while retaining non-convex convergence guarantees.
Deep Learning with Differential Privacy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Private Rate-Constrained Optimization with Applications to Fair Learning
RaCO-DP is a differentially private SGDA algorithm that enforces arbitrary prediction-rate constraints, such as group fairness and false negative rate limits, using a private histogram per mini-batch while retaining non-convex convergence guarantees.