Stabilizing updates in differentially private stochastic gradient descent with buffered rejection
Differentially private stochastic gradient descent is a standard algorithm for training deep models on sensitive data, but under tight privacy budgets it must add large noise to every step, which slows convergence and reduces accuracy. Selective update method…
<li>Hong, C., Chen, L., Liang, Y. & Zeng, Z. Stacked capsule graph autoencoders for geometry-aware 3D head pose estimation. Comput. Vis. Image Underst.208, 103224 (2021). Google Scholar </li><… [+7539 chars]