Book ; Online: Private Federated Learning with Autotuned Compression
2023
Abstract: 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, ... ...
Abstract | 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. Comment: Accepted to ICML 2023 |
---|---|
Keywords | Computer Science - Machine Learning ; Statistics - Machine Learning |
Publishing date | 2023-07-20 |
Publishing country | us |
Document type | Book ; Online |
Database | BASE - Bielefeld Academic Search Engine (life sciences selection) |
Full text online
More links
Kategorien
Inter-library loan at ZB MED
Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.