We give a procedure for computing group-level $(\epsilon, \delta)$-DP guarantees for DP-SGD, when using Poisson sampling or fixed batch size sampling. Up to discretization errors in the implementation, the DP guarantees computed by this procedure are tight (assuming we release every intermediate iterate).

翻译：我们提出了一种计算DP-SGD在泊松采样或固定批量大小采样下组级别$(\epsilon, \delta)$-差分隐私保证的方法。在忽略实现过程中离散化误差的前提下，该方法计算的差分隐私保证是紧致的（假设我们发布每次中间迭代结果）。