פונקציות של סחיטה ל-DP-SGD עם תת-קבוצות בהתבסס על אלוקציה סיכומית: גבולות עליונים ותחתונים צמודים

תקציר מקורי באנגליתarXiv:2605.06259v3 Announce Type: replace Abstract: Within the $f$-DP framework, we derive a tight analysis of the trade-off function for Differentially Private Stochastic Gradient Descent (DP-SGD) with subsampling based on random allocation in which each sample is independently assigned to exactly one of $M$ minibatches per epoch, each minibatch corresponding to one of the $M$ SGD rounds within a single epoch. Our analysis holds under an explicit validity condition, whose hypotheses together force $\sigma \geq \sqrt{3/\ln M}$, where $\sigma$ is the DP noise multiplier. Unlike $f$-DP analyses for Poisson subsampling, which yield non-closed implicit formulas that can be machine computed but are non-transparent, random allocation admits a tight analysis yielding transparent and interpretable