The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization

ArXi:2605.16219v1 Announce Type: new Differential privacy changes the effective sample size governing CVaR learning. For tail mass $\tau$, the privacy-relevant sample size is not $n$, but $n\tau$; equivalently, the effective private tail sample size is $\epsilon n\tau$. Private CVaR excess risk decomposes into ordinary tail-risk statistical error and a privacy price.