Roummel Marcia

The paper introduces Fractional-Order Differentially Private Stochastic Gradient Descent (FO-DP-SGD), a mechanism that incorporates fractional memory into the gradient release process to improve privacy-utility trade-offs in private optimization.

The paper introduces SMA-DP-SGD, a Spectral Memory-Aware Differential Privacy method that enhances standard DP-SGD by incorporating a memory branch derived from past noisy updates, improving model utility on challenging datasets.