Beyond Conventional Federated Learning via High-Order Regularization
This story is from 2026-09-10. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.09904v1 Announce Type: cross Abstract: Federated clients that perform several local optimization steps can return parameter displacements with widely different magnitudes. The quadratic regularization of FedProx grows linearly with displacement and therefore offers limited control over t…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-10 04:00 · arXiv stat.ML
Beyond Conventional Federated Learning via High-Order Regularization