Timezone: »

Private Federated Learning with Autotuned Compression
Enayat Ullah · Christopher Choquette-Choo · Peter Kairouz · Sewoong Oh

Tue Jul 25 05:00 PM -- 06:30 PM (PDT) @ Exhibit Hall 1 #406

We propose new techniques for reducing communication in private federated learning without the need for setting or tuning compression rates. Our on-the-fly methods automatically adjust the compression rate based on the error induced during training, while maintaining provable privacy guarantees through the use of secure aggregation and differential privacy. Our techniques are provably instance-optimal for mean estimation, meaning that they can adapt to the ``hardness of the problem'' with minimal interactivity. We demonstrate the effectiveness of our approach on real-world datasets by achieving favorable compression rates without the need for tuning.

Author Information

Enayat Ullah (Johns Hopkins University)
Christopher Choquette-Choo (Google Deepmind)
Peter Kairouz (Google)
Sewoong Oh (University of Washington)

More from the Same Authors