Timezone: »

Differentially Private Learning with Adaptive Clipping
Galen Andrew · Om Thakkar · Brendan McMahan · Swaroop Ramaswamy

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @

Existing approaches for training neural networks with user-level differential privacy (e.g., DP Federated Averaging) in federated learning (FL) settings involve bounding the contribution of each user's model update by {\em clipping} it to some constant value. However there is no good {\em 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. We propose a method wherein instead of a fixed clipping norm, one clips to a value at a specified quantile of the update norm distribution, where the value at the quantile is itself estimated online, with differential privacy. The method tracks the quantile closely, uses a negligible amount of privacy budget, is compatible with other federated learning technologies such as compression and secure aggregation, and has a straightforward joint DP analysis with DP-FedAvg. Experiments demonstrate that adaptive clipping to the median update norm works well across a range of federated learning tasks, eliminating the need to tune any clipping hyperparameter.

Author Information

Galen Andrew (Google)
Om Thakkar (Google)
Brendan McMahan (Google Research)
Swaroop Ramaswamy (Google)

More from the Same Authors