Bring Y our Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

Neural Information Processing Systems 

We provide a general framework for solving differentially private stochastic minimax optimization (DP-SMO) problems, which enables the practitioners to bring their own base optimization algorithm and use it as a black-box to obtain the near-optimal privacy-loss trade-off.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found