Skip to yearly menu bar Skip to main content


Compression with Exact Error Distribution for Federated Learning

Mahmoud Hegazy · RĂ©mi Leluc · Cheuk Ting Li · Aymeric Dieuleveut

MR1 & MR2 - Number 134
[ ]
Fri 3 May 8 a.m. PDT — 8:30 a.m. PDT


Compression schemes have been extensively used in Federated Learning (FL) to reduce the communication cost of distributed learning. While most approaches rely on a bounded variance assumption of the noise produced by the compressor, this paper investigates the use of compression and aggregation schemes that produce a specific error distribution, e.g., Gaussian or Laplace, on the aggregated data. We present and analyze different aggregation schemes based on layered quantizers achieving exact error distribution. We provide different methods to leverage the proposed compression schemes to obtain compression-for-free in differential privacy applications. Our general compression methods can recover and improve standard FL schemes with Gaussian perturbations such as Langevin dynamics and randomized smoothing.

Live content is unavailable. Log in and register to view live content