Importance matching lemma for lossy compression with side information
We propose two extensions to existing importance sampling based methods for lossy
compression. First, we introduce an importance sampling based compression scheme that is …
compression. First, we introduce an importance sampling based compression scheme that is …
Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
We study the mean estimation problem under communication and local differential privacy
constraints. While previous work has proposed order-optimal algorithms for the same …
constraints. While previous work has proposed order-optimal algorithms for the same …
AQUILA: Communication Efficient Federated Learning With Adaptive Quantization in Device Selection Strategy
The widespread adoption of Federated Learning (FL), a privacy-preserving distributed
learning methodology, has been impeded by the challenge of high communication …
learning methodology, has been impeded by the challenge of high communication …
Leveraging Side Information for Communication-Efficient Federated Learning
The high communication cost of sending model updates from the clients to the server is a
significant bottleneck for scalable federated learning (FL). Among existing approaches, state …
significant bottleneck for scalable federated learning (FL). Among existing approaches, state …
[PDF][PDF] Minimal Communication-Cost Statistical Learning
M Sefidgaran, A Zaidi, P Krasnowski - arXiv e-prints, 2024 - arxiv.org
A client device which has access to n training data samples needs to obtain a statistical
hypothesis or model W and then to send it to a remote server. The client and the server …
hypothesis or model W and then to send it to a remote server. The client and the server …
Exact Optimality in Communication-Privacy-Utility Tradeoffs
We study the mean estimation problem under communication and local differential privacy
constraints. While previous work has proposed order-optimal algorithms for the same …
constraints. While previous work has proposed order-optimal algorithms for the same …