We consider the problem of hyperparameter tuning in training neural networks with user-level differential privacy (DP). Existing approaches for DP training (e.g., DP Federated Averaging) involve bounding the contribution of each user's model update by *clipping* them to a fixed norm. However there is no good *a priori* setting of the clipping norm across tasks and learning settings: the update norm distribution depends on the model architecture and loss, the amount of data on each device, the client learning rate, and possibly various other parameters. In this work, we propose a method wherein instead of using a fixed clipping norm, one clips to a value at a specified quantile of the distribution of update norms, where the value at the quantile is itself estimated online, with differential privacy. Experiments demonstrate that adaptive clipping to the median update norm works well across a range of federated learning problems, eliminating the need to tune any clipping hyperparameter.
翻译:我们考虑了在培训神经网络时使用用户级差异隐私(DP)的超参数调整问题。现有的DP培训方法(例如,DP Federed Averageing)涉及将每个用户的模型更新贡献通过* clipping * 约束到固定规范。然而,没有好的 * a requiti * 设置跨任务和学习环境的剪裁规范:更新的规范分配取决于模型结构和损失、每个设备的数据数量、客户学习率以及可能的其他参数。在这个工作中,我们提出了一种方法,其中不使用固定剪裁规范,而是将一个剪剪到更新规范分配的某个特定数量的价值的剪辑,在这种数量上,对四分位数的数值本身进行在线估算,并有不同的隐私性。实验表明,对中位更新规范的调整剪辑在一系列联邦化学习问题中运作良好,因此不需要调整任何剪裁超参数。